headron
Skill3 starsChanged 15 days agoMITView on GitHub
Route, gate, verify and search the Headron engineering atlas. Use before editing any file in a Headron checkout, to find which gate proves a change, or to look up a Headron rule, ledger entry or command.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- HLIntel/Headronword for word, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 1
- HLIntel/Headron★ 3100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms.txtllms.txt
- headronSkill
- landSkill
- rekickSkill
- syncSkill
- run-workflowSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
No count typed into prose — generate it or name the instrument that prints it.
- Distinctive: line 35
No calendar date — stamp with contract version.
- Very specific: line 36
No tool name in prose — tools live in languages/<route>/tools.yaml.
- Very specific: line 38
Every limit names its closer — all instruments carry proves, does_not_prove, closed_by.
- Very specific: line 39
Never raise a cap to fit your code — code_shape and context_policy ratchets only fall.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
Headron — Engineering Atlas skill
Route first. Load only what the route names. Never read breadth-first.
Entry
python scripts/atlas.py port <file|dir|.> --frame agent --jsonReturns: route, tier, gates, lessons, next steps. Every other command follows from the port.
python scripts/atlas.py find <query> [--snippet] [--exact] # instant autonomous search
python scripts/atlas.py sweep [target] [--line] # fast semantic sweep of tiers & shards
python scripts/atlas.py gate <path> <gate> # cheapest single-gate answer
python scripts/atlas.py plan <path> --task <t> --change <class> --json
python scripts/atlas.py check # contract validity; exit code is verdict
python scripts/verify.py # full done-set; exit code is verdict
python scripts/atlas.py doctor --json # environment health
python scripts/atlas.py failures # mistake ledger
python scripts/branchstate.py --land # land a branch (never bare-push)Hooks: shell headron shell --json "<cmd>" · edit headron port <file> --line · done headron verify
Rules that fail the build
- No count typed into prose — generate it or name the instrument that prints it.
- No calendar date — stamp with contract version.
- No tool name in prose — tools live in
languages/<route>/tools.yaml; documents name gates. - Refuse rather than invent —
noneis a real answer. - Every limit names its closer — all instruments carry
proves,does_not_prove,closed_by. - Never raise a cap to fit your code —
code_shapeandcontext_policyratchets only fall. - A change ends when the artifact parses — every tracked source and JSON file must parse.
- A control with no enforcer is refused.
Change classes
source_change · api_change · dependency_change · security_sensitive ·
concurrency_change · performance_change · retrieval_change
Pick the class, satisfy its gates, verify on the exit code — never on a line of output.
Done-set gates
contract · planted_suite · agent_controls · code_shape · examples · context_cost ·
markdown · cli_smoke · cidrift · index_check · invariants · lint · format ·
typecheck · own_enforcement · secret_scan · workflow_lint · workflow_audit
Where to put what
- Repeated fact:
atlas.yamlplus a generated block. - Language tool: its pack's
tools.yaml. - New rule: its own
*_errors()and planted defect. - Example:
examples/, and it must run.
Intents
Asked to use / install / open / run / pull / report? → llms.txt, then When asked to.
Directed into a role? → headron role. Picking up interrupted work? → headron resume.
--json records are frozen in tools/atlas-output.schema.json: depend on those ids.
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.

