Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/hams-ollo/zen-agent-skills/init-worktrackingnpx skills add hams-ollo/zen-agent-skills --skill init-worktrackinggit clone --depth 1 https://github.com/hams-ollo/zen-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hams-ollo/zen-agent-skills/init-worktracking)<a href="https://agentmods.dev/skills/hams-ollo/zen-agent-skills/init-worktracking"><img src="https://agentmods.dev/badge/skills/hams-ollo/zen-agent-skills/init-worktracking.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00207 | $0.04531 |
| Opus 5 | $0.00103 | $0.02266 |
| Sonnet 5 | $0.00041 | $0.00906 |
| Haiku 4.5 | $0.00021 | $0.00453 |
Grade A, and why
init-worktracking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init-worktracking
Scaffold a spec-driven, low-context-bloat work-tracking system into whatever repository this is invoked from. The system is separate files at four altitudes of work, so an assigned agent loads only what its task needs:
AGENTS.md- global rules, including the agent reading protocol (read this file + your one task file + only itstouched_files)..tasks/- atomic, agent-assignable task files, one per work item, withdone/for completed ones and a shippedvalidate.py.ROADMAP.md- the strategic Epic/Feature layer.CHANGELOG.md- append-only ledger of finished tasks.CLAUDE.mdand optional Cursor/Copilot files - thin pointers toAGENTS.md, the one canonical source every agent flavor reads.
Templates live in templates/. Fill their {{PLACEHOLDERS}} from the actual repo and write them in, without clobbering anything that already exists.
Why this shape
The point is context frugality for agents. A task file's touched_files frontmatter is a read/write whitelist, depends_on is a safe-dispatch guard for parallel agents, and the acceptance criteria are a mechanically checkable command the agent self-verifies against. That is exactly the unit the fix-batch skill consumes: one task file per parallel worktree-isolated agent, and the unit the new-task skill authors. So the scaffold is only as good as the honesty of those fields, which is why a validator ships with it.
Footprint tiers
Do not dump the whole system on a 200-line project. Ask which tier fits, or infer from repo size and let the user correct:
| Tier | Writes | For |
|---|---|---|
| lite | AGENTS.md, .tasks/ (README, _TEMPLATE.md, validate.py, done/), CLAUDE.md pointer |
small or solo repos that want task files without the ceremony |
| standard | lite + ROADMAP.md + CHANGELOG.md |
most repos; the full altitude model |
| team | standard + a CI/pre-commit invocation of the validator + optional Cursor/Copilot pointers | repos with many contributors or agents, where drift must be caught mechanically |
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- templates/_TEMPLATE.md.tmpl 4.0 KB
- templates/AGENTS.md.tmpl 2.9 KB
- templates/CHANGELOG.md.tmpl 447 B
- templates/CLAUDE.md.tmpl 236 B
- templates/copilot-instructions.md.tmpl 258 B
- templates/cursor-rule.mdc.tmpl 333 B
- templates/ROADMAP.md.tmpl 1.1 KB
- templates/tasks-README.md.tmpl 4.7 KB
- templates/validate.py 29 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · +7 lines 8089e4d31d11
- 5d ago First seen · 182 lines · 207 tokens per session scan A 1424bb6f9ef5
init-worktracking is a skill published in the GitHub repository hams-ollo/zen-agent-skills (2 stars, last pushed 4d ago), licensed MIT. It adds 207 tokens to every session and 4,531 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
review
Use when explicitly invoked to review a branch diff (or any diff or files pointed at) with a find-only subagent covering rubric and conventions, change conformance against the AC-N and their runtime-verification evidence, and documentation consistency — one plain-text verdict that reaches lgtm only when no dimension…
implement
Use when explicitly invoked to execute a change's tasks.md from the first unticked step: implement each task, run its validation, commit, then run the quality gate and verify every acceptance criterion by observed behavior. Needs no conversation context — the change folder is the whole input. Trigger on…
ship
Use when explicitly invoked to run the whole change ladder without stopping — ticket, plan, implementation, quality gate, runtime verification, review to lgtm — deciding every open question autonomously and recording each decision in proposal.md. Trigger on '/sw:ship', '$sw:ship', or a request to take something from…
archive
Use when explicitly invoked to close out a change whose branch has already merged: confirm the merge from git alone, then move the change folder under changes/archive/ with its ship date. Trigger on '/sw:archive', '$sw:archive', 'archive this change', or a request to close out a merged change.
gsd-audit-milestone
Audit milestone completion against original intent before archiving.
spec-kitty-charter-doctrine
Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…