Skip to content

docs(#6231): require runtime discovery for agent/skill inventory refs - #6234

Open
fullsend-ai-coder[bot] wants to merge 1 commit into
mainfrom
agent/6231-discovery-over-hardcoded
Open

docs(#6231): require runtime discovery for agent/skill inventory refs#6234
fullsend-ai-coder[bot] wants to merge 1 commit into
mainfrom
agent/6231-discovery-over-hardcoded

Conversation

@fullsend-ai-coder

Copy link
Copy Markdown
Contributor

Summary

Adds a repo-level rule to AGENTS.md requiring runtime discovery commands (not hardcoded tables) when writing content that references the fullsend agent/skill/sub-agent inventory. This prevents the rework pattern observed in PR #6202, where a code agent synthesized a static inventory from training data that went stale immediately.

Changes

  • Added a new bullet to the "How to work in this repo" section of AGENTS.md, placed after the existing documentation rules
  • The rule directs contributors to use runtime discovery against fullsend-ai/agents and references the author-fullsend-augmentations skill for concrete patterns

Testing

  • gitlint --commit HEAD passes
  • No Go code changed — no test suite or coverage impact
  • Secret scan clean

Closes #6231

Post-script verification

  • Branch is not main/master (agent/6231-discovery-over-hardcoded)
  • Secret scan passed (gitleaks — 4bfc8988be00438547d53e2d4ab1fa4211563eaa..HEAD)
  • PR body secret scan passed (gitleaks — no-git)

Add a rule to AGENTS.md requiring runtime discovery commands
against fullsend-ai/agents when referencing the agent, skill,
or sub-agent inventory. Hardcoded static tables go stale because
the agents repo evolves independently. This rule prevents the
rework pattern observed in PR #6202, where a code agent produced
a hardcoded inventory that required a near-total rewrite.

Points readers to the author-fullsend-augmentations skill for
concrete discovery patterns.

Note: pre-commit could not run in the sandbox due to network
restrictions (git fetch blocked). The post-script runs
pre-commit authoritatively on the runner.

Closes #6231
@fullsend-ai-coder
fullsend-ai-coder Bot requested a review from a team as a code owner August 14, 2026 16:53
@fullsend-ai-coder fullsend-ai-coder Bot added the ready-for-review Agent PR ready for human review label Aug 14, 2026
@fullsend-ai-review

fullsend-ai-review Bot commented Aug 14, 2026

Copy link
Copy Markdown

🤖 Finished Review · ✅ Success · Started 4:55 PM UTC · Completed 5:07 PM UTC

Commit: 4b503a1 · View workflow run →

@codecov

codecov Bot commented Aug 14, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

@fullsend-ai-review

Copy link
Copy Markdown

Review

Findings

Medium


Labels: PR modifies AGENTS.md, a documentation/governance file

@fullsend-ai-review fullsend-ai-review Bot added requires-manual-review Review requires human judgment component/docs User-facing documentation Review effort 1/5 labels Aug 14, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

component/docs User-facing documentation ready-for-review Agent PR ready for human review requires-manual-review Review requires human judgment Review effort 1/5

Projects

None yet

Development

Successfully merging this pull request may close these issues.

AGENTS.md: require runtime discovery for content referencing skill/agent inventories

0 participants