ticket-index-skills
AGENTS.md1 starsChanged 26 days agoMITView on GitHub
A kit of agent skills built around ticket-index: a generated, three-level index over Markdown tickets. The core skill and its Python script live in skills/ticket-index/. Companion skills cover the ticket lifecycle and the disciplines around it. README.md explains the workflow; docs/ holds the concepts and reference. Run verify.py before claiming a change is complete. It is the same command CI runs. - Ticket frontmatter is the source of truth. Never store a derived fact (status, owner, counts, hierarchy) in the…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 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 repository17 other files it gives its agents.
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- grillingSkill
- handoffSkill
- implementSkill
- implement-specSkill
- prototypeSkill
- prSkill
- setup-ticket-workflowSkill
- tddSkill
- ticket-indexSkill
- to-specSkill
- to-ticketsSkill
- wayfinderSkill
- writing-for-agentsSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 17
Run verify.py before claiming a change is complete.
- Very specific: line 26
Keep render deterministic: no timestamps, absolute paths, network access, or unordered iteration in the output path.
- Very specific: line 29
If you copy material from another project, record its author, license, and URL in THIRD-PARTY-NOTICES.md.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md
What this repository is
A kit of agent skills built around ticket-index: a generated, three-level index over
Markdown tickets. The core skill and its Python script live in
skills/ticket-index/. Companion skills cover the ticket lifecycle and the disciplines
around it. README.md explains the workflow; docs/ holds the concepts and reference.
Commands
python scripts/verify.py # unit tests + demo cycle + installer
python -m unittest discover -s tests -v # unit tests onlyRun verify.py before claiming a change is complete. It is the same command CI runs.
Rules
- Ticket frontmatter is the source of truth. Never store a derived fact (status, owner,
counts, hierarchy) in the generated index or in
ticket-index.toml. docs/tickets/,examples/demo/docs/tickets/, and any file containing<!-- generated by ticket-index; do not edit -->are generated. Change the tickets or the configuration, then runrender.- Keep
renderdeterministic: no timestamps, absolute paths, network access, or unordered iteration in the output path. - A new behaviour needs a test in
tests/before or with the code. - If you copy material from another project, record its author, license, and URL in
THIRD-PARTY-NOTICES.md.
Conventions
- Skills:
skills/<name>/SKILL.md, withnameanddescriptionfrontmatter. Addagents/openai.yamlfor user-invoked skills. Keep reference material in sibling files. - Python: 3.11+, standard library only. The index script must not grow dependencies.
- Markdown: English scaffolding; ticket summaries and bodies may use any language.
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.