plugin-development
Skill0 starsChanged 4 days agoApache-2.0View on GitHub
Adds, changes, or removes a skill or the agent shipped by the harness-md plugin, end to end: OpenSpec change with behavioural test scenarios, implementation to the skill quality bar and the plugin's contract, client file generation, checks, behavioural tests through subagents, and per-client verification. Use when asked to add or modify what the plugin ships, when the catalog or skills check fails, or when a client stops loading a component. Not for the HARNESS.md format or its validator (read the format-changes knowledge file), hub entries, or GitHub issue and pull-request mechanics.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- jokob-sk/NetAlertXtheir own version, first seen Nov 1, 2026
- netalertx/NetAlertXtheir own version, first seen Nov 1, 2026
- nimadorostkar/Claude-Skills-collectiontheir own version, first seen Oct 13, 2026
- prismatic7/agy-plugin-developmenttheir own version, first seen Oct 9, 2026
- matrixorigin/Memoriatheir own version, first seen Oct 8, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- jokob-sk/NetAlertX★ 7.4ksame name
- netalertx/NetAlertX★ 7.4ksame name
- matrixorigin/Memoria★ 624same name
- nimadorostkar/Claude-Skills-collection★ 37same name
- prismatic7/agy-plugin-development★ 0same name
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 repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- github-project-workflowSkill
- human-writingSkill
- openspec-apply-changeSkill
- openspec-archive-changeSkill
- openspec-exploreSkill
- openspec-proposeSkill
- openspec-sync-specsSkill
- openspec-update-changeSkill
- authority-buildingSkill
- completion-buildingSkill
- entropy-buildingSkill
- environment-buildingSkill
- feedback-buildingSkill
- gates-buildingSkill
- harness-architectureSkill
- harness-auditSkill
- harness-buildSkill
- harness-designSkill
- harness-extractSkill
- harness-mdSkill
- knowledge-buildingSkill
- lightweight-spec-workflowSkill
- openspec-workflowSkill
- project-skill-buildingSkill
- spec-driven-developmentSkill
- spec-kit-workflowSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 2 are distinctive, and 8 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Every shipped entry lives in exactly one catalog (skill or agent) and is described by exactly one spec.
- Very specific: line 24
Read .agents/knowledge/plugin-architecture.md before deciding what to add: every skill produces, reads, or builds from a project's …
- Distinctive: line 38
Define: Write down the task the skill covers (one coherent unit of work), its kind, its triggers including indirect phrasings, what the …
- Very specific: line 42
If a bare agent already does the task well, stop: the skill adds nothing.
- Very specific: line 52
Spec, tests first: Read .agents/knowledge/spec-workflow.md.
- Very specific: line 53
Run the openspec-propose skill with the capability path skill/<name> or agent/<name>.
- Very specific: line 59
Stop until the pull request carries spec:approved.
- Distinctive: line 93
Run the spec's trigger prompts and outcome tasks through clean-context subagents on the least capable model tier available.
- Very specific: line 105
Finish: Update the skill tables of README.md and README.zh.md and the plugin pages of the site in both languages.
- Very specific: line 112
Delete the implementation and the spec in one change (a delta spec with ## REMOVED Requirements.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Plugin development
Every shipped entry lives in exactly one catalog (skill or agent)
and is described by exactly one spec; just validate enforces the pairing.
Work spec first, and treat the spec's scenarios
as the entry's behavioural tests.
Rules on every step
- Read
.agents/knowledge/plugin-architecture.mdbefore deciding what to add: every skill produces, reads, or builds from a project'sHARNESS.md, and a new skill has to fit one of the kinds there (format, workflow, manual, layer builder, daily). - Read
.agents/knowledge/skill-quality.mdbefore writing any file underskills/. - A skill is self-contained: it links to nothing outside its directory,
names other shipped skills by role only
(
harness-verifieris the one name allowed), and deposits nothing in a target project that names the plugin. - Fix findings at their source; never edit a generated file or relax a check.
Workflow
- Define. Write down the task the skill covers (one coherent unit of work),
its kind, its triggers including indirect phrasings,
what the agent lacks without it,
and its invocation mode (user-invoked only for the four workflows).
If a bare agent already does the task well, stop: the skill adds nothing.
A new layer is a format change first (
.agents/knowledge/format-changes.md); a new builder without a new layer cannot exist, because each layer has exactly one. - Budget. Descriptions share 8,000 characters:
a layer builder at most 240, a workflow at most 400,
any other skill at most 700.
just skills-checkprints every length and the total; when the total would pass the budget, cut another description in the same change. - Spec, tests first. Read
.agents/knowledge/spec-workflow.md. Run theopenspec-proposeskill with the capability pathskill/<name>oragent/<name>. The delta spec carries the behavioural test cases as scenarios: at least three prompts that should load the skill and three near misses that should not, and at least two outcome tasks with a result a reader can judge without the skill. State which clients the entry ships to. Stop until the pull request carriesspec:approved. - Implement by kind (read
.agents/knowledge/client-matrix.md):- any skill:
skills/<name>/SKILL.mdin the body order ofskill-quality.md; shared paragraphs copied byte for byte from.agents/knowledge/shared-blocks.md; scripts and script assets in Python with PEP 723 metadata and a_test.pyeach. - layer builder: one sentence of description containing
Owns the <Layer> layerwith a name fromscripts/lib/layers.ts; the four modes (design, extract, build, audit); the six fixed steps (Observe, Write the section, Build, Verify, Audit, Hand back); a default with its reason for every decision in step 2; the shared conventions ofplugin-architecture.md(severity scale, routes owed, audit with no section). - workflow:
disable-model-invocation: trueand anagents/openai.yamlwithpolicy.allow_implicit_invocation: false; it finds builders by the ownership phrase and names none. - format skill (
skills/harness-md/): itsreferences/specification.mdis a byte-identical copy ofspec/spec.md; change it only by copying, in a format change. - agent:
com.anthropic.claude-code/agents/<name>.mdonly (Codex and Antigravity plugins carry no agents;just validaterejects anagents/directory under their namespaces); read-only tools unless the spec justifies writes.
- any skill:
- Prune. Three passes over everything written: deduplicate, drop what no longer bears on the skill, delete every sentence that would not change behaviour on the weakest supported model.
- Generate and check.
just genafter any change toplugin.jsonor the agents directory;just skills-check;just check. - Behavioural tests. Run the spec's trigger prompts and outcome tasks through clean-context subagents on the least capable model tier available; trigger prompts never name the skill. Record pass or fail per scenario in the pull request's Verification section; record the degradation when no subagent is available and the prompts ran in a fresh session instead.
- Verify in clients.
just clients-validate, then load the entry by hand in at least one client (claude --plugin-dir ., the Codex marketplace,agy plugin install .thenagy plugin uninstall harness-md). Record anything that contradicts the matrix, in the matrix's verification log. - Finish. Update the skill tables of
README.mdandREADME.zh.mdand the plugin pages of the site in both languages;openspec-apply-changetracks tasks; archive perspec-workflow.md; the pull request follows thegithub-project-workflowskill.
Removing or renaming an entry
Delete the implementation and the spec in one change
(a delta spec with ## REMOVED Requirements;
a rename is a removal plus an addition),
remove or rename the README rows and the site's mentions,
run just gen and just check.
Removing a layer builder leaves a layer without an owner,
which just skills-check rejects: a layer goes only through a format change.
Gotchas
claude plugin validatefails on an unknown top-level key in.claude-plugin/plugin.json; that file is generated, so fixscripts/gen.ts.- A skill name must not also exist under
.agents/skills/; Codex and Antigravity load both directories here. - A shared block edited in one skill fails
just skills-checkuntil the canon and every other user change too. A new block is added to the canon first and must be used by at least one skill. - A reference or asset nothing in
SKILL.mdpoints to fails the check; every pointer states when to read the file. - OpenSpec strict validation fails a requirement whose text exceeds 500 characters; move cases into scenarios.
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.

