Repository navigation
docs: keep delegation snippets concise and skill-driven - #4
Merged
Merged
Conversation
There was a problem hiding this comment.
🟡 Changes recommended
Unresolved moderate snippet fallback and skill-guard findings remain.
Get a fresh assessment by requesting another Copilot review.
Pull request overview
Updates the catalog to 0.2.1 and simplifies six delegation snippets around role selection, dispatch, and optional skills.
Changes:
- Removes capacity, allocation, and runtime-evidence details.
- Adds Skill-tool invocation and fallback guidance.
- Updates documentation, changelog, README, and arrangement versions.
Review findings remain: standalone snippets each have two unresolved moderate findings; skill-enabled snippets each have four unresolved moderate findings. docs/installation.md also has one unresolved nit (1 vote) concerning contradictory Portuguese guidance.
File summaries
| File | Summary |
|---|---|
README.md |
Updates catalog version. |
docs/installation.md |
Documents snippet and skill selection. |
docs/CHANGELOG.md |
Records the 0.2.1 changes. |
arrangements/lean-delivery/arrangement.toml |
Bumps arrangement version. |
arrangements/lean-delivery/AGENTS.with-skill.snippet.md |
Adds optional skill guidance. |
arrangements/lean-delivery/AGENTS.snippet.md |
Simplifies delegation instructions. |
arrangements/balanced-delivery/arrangement.toml |
Bumps arrangement version. |
arrangements/balanced-delivery/AGENTS.with-skill.snippet.md |
Adds optional engineering guidance. |
arrangements/balanced-delivery/AGENTS.snippet.md |
Simplifies delegation instructions. |
arrangements/advanced-delivery/arrangement.toml |
Bumps arrangement version. |
arrangements/advanced-delivery/AGENTS.with-skill.snippet.md |
Adds optional engineering guidance. |
arrangements/advanced-delivery/AGENTS.snippet.md |
Simplifies delegation instructions. |
Review details
Suppressed comments (13)
arrangements/advanced-delivery/AGENTS.snippet.md:5
- The absent-skill fallback is sequenced after the native-read instruction. On a supported installation with neither a Skill tool nor
codex-orchestrationinstalled, this still tells the agent to open a nonexistentSKILL.mdbefore it can follow the fallback; guard the native read with the skill's presence.
- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
arrangements/advanced-delivery/AGENTS.with-skill.snippet.md:5
- The absent-skill fallback is sequenced after the native-read instruction. On a supported installation with neither a Skill tool nor
codex-orchestrationinstalled, this still tells the agent to open a nonexistentSKILL.mdbefore it can follow the fallback; guard the native read with the skill's presence.
- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
arrangements/advanced-delivery/AGENTS.with-skill.snippet.md:24
- The same condition-ordering problem affects the optional Pragmatic Programmer fallback: when the skill is absent and no Skill tool exists, the instruction still attempts to read a nonexistent
SKILL.md. Guard the native read withpragmatic-programmerbeing installed.
- For design tradeoffs, unclear boundaries, duplicate knowledge, an unexplained green result, or a reversible next step, invoke the Skill tool with `pragmatic-programmer` when installed. If no Skill tool exists, read its `SKILL.md` natively.
arrangements/advanced-delivery/AGENTS.with-skill.snippet.md:25
- The engineering trigger list no longer covers shared state or finite resources, even though
docs/installation.mdand the skill define that as a supported Pragmatic Programmer use case. With the skill installed, resource-ownership decisions therefore skip the optional guidance, and the absent-skill fallback also drops the ownership/release rule. Keep that trigger and fallback invariant.
- For design tradeoffs, unclear boundaries, duplicate knowledge, an unexplained green result, or a reversible next step, invoke the Skill tool with `pragmatic-programmer` when installed. If no Skill tool exists, read its `SKILL.md` natively.
- If it is not installed, state the assumptions and invariants, keep one authority per fact, explain why the result works, and choose the smallest reversible step. Do not invent tools or install skills implicitly.
arrangements/balanced-delivery/AGENTS.snippet.md:5
- The absent-skill fallback is sequenced after the native-read instruction. On a supported installation with neither a Skill tool nor
codex-orchestrationinstalled, this still tells the agent to open a nonexistentSKILL.mdbefore it can follow the fallback; guard the native read with the skill's presence.
- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
arrangements/balanced-delivery/AGENTS.with-skill.snippet.md:5
- The absent-skill fallback is sequenced after the native-read instruction. On a supported installation with neither a Skill tool nor
codex-orchestrationinstalled, this still tells the agent to open a nonexistentSKILL.mdbefore it can follow the fallback; guard the native read with the skill's presence.
- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
arrangements/balanced-delivery/AGENTS.with-skill.snippet.md:24
- The same condition-ordering problem affects the optional Pragmatic Programmer fallback: when the skill is absent and no Skill tool exists, the instruction still attempts to read a nonexistent
SKILL.md. Guard the native read withpragmatic-programmerbeing installed.
- For design tradeoffs, unclear boundaries, duplicate knowledge, an unexplained green result, or a reversible next step, invoke the Skill tool with `pragmatic-programmer` when installed. If no Skill tool exists, read its `SKILL.md` natively.
arrangements/balanced-delivery/AGENTS.with-skill.snippet.md:25
- The engineering trigger list no longer covers shared state or finite resources, even though
docs/installation.mdand the skill define that as a supported Pragmatic Programmer use case. With the skill installed, resource-ownership decisions therefore skip the optional guidance, and the absent-skill fallback also drops the ownership/release rule. Keep that trigger and fallback invariant.
- For design tradeoffs, unclear boundaries, duplicate knowledge, an unexplained green result, or a reversible next step, invoke the Skill tool with `pragmatic-programmer` when installed. If no Skill tool exists, read its `SKILL.md` natively.
- If it is not installed, state the assumptions and invariants, keep one authority per fact, explain why the result works, and choose the smallest reversible step. Do not invent tools or install skills implicitly.
arrangements/lean-delivery/AGENTS.snippet.md:5
- The absent-skill fallback is sequenced after the native-read instruction. On a supported installation with neither a Skill tool nor
codex-orchestrationinstalled, this still tells the agent to open a nonexistentSKILL.mdbefore it can follow the fallback; guard the native read with the skill's presence.
- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
arrangements/lean-delivery/AGENTS.with-skill.snippet.md:5
- The absent-skill fallback is sequenced after the native-read instruction. On a supported installation with neither a Skill tool nor
codex-orchestrationinstalled, this still tells the agent to open a nonexistentSKILL.mdbefore it can follow the fallback; guard the native read with the skill's presence.
- Before delegating or reconciling deliveries, invoke the Skill tool with `codex-orchestration` when installed. If no Skill tool exists, read its `SKILL.md` through the native file-reading interface. If the skill is not installed, follow the rules below.
arrangements/lean-delivery/AGENTS.with-skill.snippet.md:24
- The same condition-ordering problem affects the optional Pragmatic Programmer fallback: when the skill is absent and no Skill tool exists, the instruction still attempts to read a nonexistent
SKILL.md. Guard the native read withpragmatic-programmerbeing installed.
- For design tradeoffs, unclear boundaries, duplicate knowledge, an unexplained green result, or a reversible next step, invoke the Skill tool with `pragmatic-programmer` when installed. If no Skill tool exists, read its `SKILL.md` natively.
arrangements/lean-delivery/AGENTS.with-skill.snippet.md:25
- The engineering trigger list no longer covers shared state or finite resources, even though
docs/installation.mdand the skill define that as a supported Pragmatic Programmer use case. With the skill installed, resource-ownership decisions therefore skip the optional guidance, and the absent-skill fallback also drops the ownership/release rule. Keep that trigger and fallback invariant.
- For design tradeoffs, unclear boundaries, duplicate knowledge, an unexplained green result, or a reversible next step, invoke the Skill tool with `pragmatic-programmer` when installed. If no Skill tool exists, read its `SKILL.md` natively.
- If it is not installed, state the assumptions and invariants, keep one authority per fact, explain why the result works, and choose the smallest reversible step. Do not invent tools or install skills implicitly.
docs/installation.md:34
- The new installation wording changes the agent-facing invocation to the exact
Skilltool name, butdocs/README.pt-BR.md:42-44still says the inserted snippet calls$codex-orchestrationand$pragmatic-programmer. That public installation guide now contradicts the snippets and can direct users to runtime-dependent prompt syntax; update it alongside this documentation change.
Both snippet variants provide standalone delegation rules and invoke
`codex-orchestration` when installed. Choose `AGENTS.with-skill.snippet.md` only
when you also want the separate, optional Pragmatic Programmer engineering
section. Counts, model allocation and runtime evidence belong in the arrangement
README and configuration, not the inserted instruction section.
- Files reviewed: 12/12 changed files
- Comments generated: 6
- Review effort level: Lite
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
| Only the parent integrates, inspects the diff, and verifies responsible checks; skipped, unavailable, or mocked required checks block acceptance. | ||
| - Only the parent delegates. Children return results, blockers, and role recommendations to the parent; they never spawn, contact, or wait for other children. | ||
| - Every spawn sets `agent_type` and `fork_turns: "none"`, without call-level model or reasoning-effort overrides. | ||
| - Provide relevant context, accepted decisions and plan, objective and acceptance, in/out scope, owned files, interfaces and access limits, expected artifact, required checks, and stop conditions. Do not copy the full conversation or create a plan solely for dispatch. |
| ### Ownership and evidence | ||
| - Only the parent delegates. Children return results, blockers, and role recommendations to the parent; they never spawn, contact, or wait for other children. | ||
| - Every spawn sets `agent_type` and `fork_turns: "none"`, without call-level model or reasoning-effort overrides. | ||
| - Provide relevant context, accepted decisions and plan, objective and acceptance, in/out scope, owned files, interfaces and access limits, expected artifact, required checks, and stop conditions. Do not copy the full conversation or create a plan solely for dispatch. |
| Only the parent integrates, inspects the diff, and verifies responsible checks; skipped, unavailable, or mocked required checks block acceptance. | ||
| - Only the parent delegates. Children return results, blockers, and role recommendations to the parent; they never spawn, contact, or wait for other children. | ||
| - Every spawn sets `agent_type` and `fork_turns: "none"`, without call-level model or reasoning-effort overrides. | ||
| - Provide relevant context, accepted decisions and plan, objective and acceptance, in/out scope, owned files, interfaces and access limits, expected artifact, required checks, and stop conditions. Do not copy the full conversation or create a plan solely for dispatch. |
| ### Ownership and evidence | ||
| - Only the parent delegates. Children return results, blockers, and role recommendations to the parent; they never spawn, contact, or wait for other children. | ||
| - Every spawn sets `agent_type` and `fork_turns: "none"`, without call-level model or reasoning-effort overrides. | ||
| - Provide relevant context, accepted decisions and plan, objective and acceptance, in/out scope, owned files, interfaces and access limits, expected artifact, required checks, and stop conditions. Do not copy the full conversation or create a plan solely for dispatch. |
| Only the parent integrates, inspects the diff, and verifies responsible checks; skipped, unavailable, or mocked required checks block acceptance. | ||
| - Only the parent delegates. Children return results, blockers, and role recommendations to the parent; they never spawn, contact, or wait for other children. | ||
| - Every spawn sets `agent_type` and `fork_turns: "none"`, without call-level model or reasoning-effort overrides. | ||
| - Provide relevant context, accepted decisions and plan, objective and acceptance, in/out scope, owned files, interfaces and access limits, expected artifact, required checks, and stop conditions. Do not copy the full conversation or create a plan solely for dispatch. |
| ### Ownership and evidence | ||
| - Only the parent delegates. Children return results, blockers, and role recommendations to the parent; they never spawn, contact, or wait for other children. | ||
| - Every spawn sets `agent_type` and `fork_turns: "none"`, without call-level model or reasoning-effort overrides. | ||
| - Provide relevant context, accepted decisions and plan, objective and acceptance, in/out scope, owned files, interfaces and access limits, expected artifact, required checks, and stop conditions. Do not copy the full conversation or create a plan solely for dispatch. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Arrangement or component and purpose
Keep insertable instructions focused on behavior rather than configuration inventories or evidence navigation. References #1.
Changes
Functional evidence
All three arrangements and 35 TOMLs pass catalog validation; component preflight and all 37 existing behavioral tests pass. Manual inspection confirms the snippet headings, inline skill calls, and removal of capacity/evidence navigation. No new native inference was run for this documentation-only correction; existing runtime limits remain documented separately.
Checks