portable-agent-repository-kit
Copilot instructions1 starsChanged 2 months agoApache-2.0View on GitHub
AGENTS.md is this repository's canonical instruction contract. Follow it before making changes. Reusable task workflows live under .agents/skills/. Use repository-owned commands, especially make doctor and make check. Preserve unrelated changes, keep validation claims evidence-based, and do not perform remote or release actions without explicit authorization. Consider Goblin Council when a coding task benefits from staged independent review: cross-component changes, architecture or public API/schema changes, authentication, untrusted inputs, or shared-state and concurrency behavior. Use its routing policy to distinguish direct Single…
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 2,349 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 repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-workboardSkill
- clear-writingSkill
- documentation-impactSkill
- github-state-auditSkill
- gitignore-auditSkill
- milestone-deliverySkill
- repository-checkSkill
- repository-delivery-gateSkill
- repository-orientationSkill
- resumable-worktree-runSkill
- security-reviewSkill
- session-usage-auditSkill
- template-project-creatorSkill
- agent-workboardSkill
- clear-writingSkill
- documentation-impactSkill
- github-state-auditSkill
- gitignore-auditSkill
- milestone-deliverySkill
- repository-checkSkill
- repository-delivery-gateSkill
- repository-orientationSkill
- resumable-worktree-runSkill
- security-reviewSkill
- session-usage-auditSkill
- template-project-creatorSkill
The file
We split this copilot-instructions.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 6
Use repository-owned commands, especially make doctor and make check.
- Distinctive: line 12
Consider Goblin Council when a coding task benefits from staged independent review: cross-component changes, architecture or public …
- Distinctive: line 21
Follow the extension's setup guide and supported-model requirements before use.
≈ “Common” is an estimate: at least 1 in 5 of the 3,779 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
GitHub Copilot Adapter
AGENTS.md is this repository's canonical instruction contract. Follow it before
making changes. Reusable task workflows live under .agents/skills/.
Use repository-owned commands, especially make doctor and make check. Preserve
unrelated changes, keep validation claims evidence-based, and do not perform remote
or release actions without explicit authorization.
Goblin Council
Consider Goblin Council when a coding task
benefits from staged independent review: cross-component changes, architecture or
public API/schema changes, authentication, untrusted inputs, or shared-state and
concurrency behavior. Use its routing policy to distinguish direct Single work,
draft-and-judge Cascade, and parallel independent Critique. Keep simple tasks
direct; use goblin-max only when the user explicitly requests it.
Goblin Council currently runs in Codex. In Copilot, recommend a Codex handoff when
the council is warranted; do not claim to execute its Codex sandboxed stages.
Follow the extension's setup guide and supported-model requirements before use;
do not silently install it or substitute unavailable models. Its review supplements
the repository's checks and conditional owner-review policy, and does not grant
permission to push, merge, or release. Follow docs/OWNER_REVIEW_POLICY.md; never
describe an owner-authored PR as independently human-reviewed, and never infer a
generated project's identities from PARK's source policy.
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.