Borrowing it
Nothing to install: this file belongs to tacoda/keystone. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tacoda/keystone/main/.claude/skills/keystone-task/SKILL.mdgit clone --depth 1 https://github.com/tacoda/keystoneWrote 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/tacoda/keystone/keystone-task)<a href="https://agentmods.dev/skills/tacoda/keystone/keystone-task"><img src="https://agentmods.dev/badge/skills/tacoda/keystone/keystone-task/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tacoda/keystone/keystone-task"><img src="https://agentmods.dev/badge/skills/tacoda/keystone/keystone-task.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00010 | $0.00675 |
| Opus 5.5 | $0.00004 | $0.00270 |
| Sonnet 5.5 | $0.00002 | $0.00135 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
keystone-task 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 1mo 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task
End-to-end task workflow. Orchestrates spec → orient → (implementation) → check-drift → verify → review and an optional learn pass at the end. The canonical phrase to kick off a unit of work.
Invoke as: "run task on <ticket-or-description>" — or just "run the task workflow."
Activities
The agent walks through each phase below in order. After each phase, pause for the user's acceptance before proceeding to the next. Do not race ahead.
- spec — read
spec.md. Author the spec, restate intent, list acceptance criteria, list non-goals, flag uncertainty. Save it. Gate: explicit user acceptance. - orient — read
orient.md. ReadCODEBASE_STATE.md, load idioms for the touched region, sketch a plan. Gate: explicit user acceptance of the plan. - implementation — read
.charter/guides/process/implementation.md. Make the changes inside the loaded idioms. Iron law: surgical edits only — touch what the spec requires. - check-drift — read
check-drift.md. Fast diff-vs-guides comparison before running heavyweight sensors. - verify — read
verify.md. Run lint, type-check, test, build, drift, commit-message sensors in this turn. Iron law: no completion claims without fresh evidence. - review — read
review.md. Run functional / security / risk / deployment review (parallel sub-agents if supported) plus spec-adherence against the acceptance criteria. - learn (conditional) — if something surprising came up during the task, read
learn.mdand capture it tolearning/inbox/. Otherwise skip.
Iron laws (carry across every phase)
- No proceeding without explicit acceptance criteria. The spec gate is real.
- No completion claims without fresh verification evidence. Sensors must run this turn.
- No commits with failing sensors. Never
--no-verify. - No AI attribution in commits, PRs, or tracker comments.
- No silent overwrites of state files.
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.
- 1mo ago First seen · 41 lines · 10 tokens per session scan A ec82e81cb4ce
keystone-task is a skill published in the GitHub repository tacoda/keystone (44 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 675 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.