Human-on-exception
Copilot instructions1 starsChanged 46 days agoMITView on GitHub
For PRs that add or change mutations reachable from authenticated UI/API, review the MUST requirements in the audit rule. SIT requirements are in docs/rules/system-test-strategy.md §4.1. Apply ai-review.md in full as a separate-context reviewer, not the implementer. Independently inspect accepted Answers / Issue AC, current-state SoT, applicable concept / active ADR / Policy, diff, and tests. Do not treat implementer self-review or the implementer's completion claim as independent evidence. Required SoT/docs audit: derive all artifacts affected by a behavior or contract…
Where files are headingNew Copilot instructions files have more rules about branches and pull requests, and fewer about code style.
Of the Copilot instructions files we read, the 2,397 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/01-audit-ui-persistence.mdcCursor rule
- independent-reviewSkill
The file
We split this copilot-instructions.md into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
do not add speculative praise
- Distinctive: line 26
when no issue exists, say so concisely
- Distinctive: line 27
do not follow AGENTS task-execution procedure as an implementation agent.
- Distinctive: line 29
if change intent is unclear, do not invent it
≈ “Common” is an estimate: at least 1 in 5 of the 3,854 Copilot instructions files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Response language
- Follow
docs/rules/language-policy.md. Choose the human-facing language in this order: (1) an explicit language instruction for the current material or output; (2) when editing an existing human-facing artifact, preserve that artifact's current language unless translation or language normalization is explicitly in scope; (3) for new human-facing material, reviews, or responses, use the language of the controlling request, requirement, or Answers; (4) if that signal is absent or genuinely ambiguous, use the existing project/document language.
Rules
- Procedure / completion / SoT:
AGENTS.md - Member-facing mutation audit source of truth:
docs/rules/audit-ui-persistence.md - Human-facing language selection and translation:
docs/rules/language-policy.md
Backend: UI-path persistence and audit
For PRs that add or change mutations reachable from authenticated UI/API, review the MUST requirements in the audit rule. SIT requirements are in docs/rules/system-test-strategy.md §4.1.
Independent review
Apply ai-review.md in full as a separate-context reviewer, not the implementer. Independently inspect accepted Answers / Issue AC, current-state SoT, applicable concept / active ADR / Policy, diff, and tests. Do not treat implementer self-review or the implementer's completion claim as independent evidence.
Required SoT/docs audit: derive all artifacts affected by a behavior or contract change and check for missing or stale tests, API/types/generated outputs, flow / ui / validation / db, transitions, and packs even when those files are absent from the PR diff. Cite the agreed target contract and concrete omission; respect the current-state SoT order and justified N/A boundaries.
Review priority
- prioritize risk detection over implementation suggestions
- prioritize potential bugs
- do not add speculative praise
- when no issue exists, say so concisely
- do not follow AGENTS task-execution procedure as an implementation agent; prioritize review responsibilities
- review rather than implement fixes
- if change intent is unclear, do not invent it
- include impact scope and reproduction condition in findings
- prioritize behavior risk, maintainability risk, and specification deviation over style-only comments
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

