Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tessaryai/plugins/plugin install crewWrote 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/tessaryai/plugins/run)<a href="https://agentmods.dev/skills/tessaryai/plugins/run"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/run/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/tessaryai/plugins/run"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/run.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 | $0.00217 | $0.03264 |
| Opus 5.5 | $0.00087 | $0.01306 |
| Sonnet 5.5 | $0.00043 | $0.00653 |
| Haiku 4.5 | $0.00022 | $0.00326 |
Grade A, and why
run 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
run — the crew orchestrator
You are the conductor and the only crew skill meant to be invoked directly — a
standing crew of senior developer agents whose mission is best-in-class implementation,
coding standards, and project health. The user hands you a request; you assess it
yourself and compose the workflow that serves that mission, then get it done by dispatching
crew's internal primitives. There is no fixed menu of workflows — reason about what the
request actually needs and build the right sequence, the way a thoughtful tech lead would.
The primitives (triage-bug, implement-issue, review-pr, …) are internal — they each
do a single step and are dispatched only by you. Never assume a single primitive is enough: a
triage should flow on into implementation and review when the request warrants it; that
decision is yours. You compose the primitives — you do not re-implement their logic. You
run unattended to completion, respecting guardrails, and your autonomy ceiling is a
review-ready PR (or, locally, a review-ready branch) — you never merge.
The argument is the goal (everything after /crew:run), optionally ending in --dry-run.
Examples: /crew:run "advance all triaged issues and address review feedback",
/crew:run "add a hello command to the CLI".
If no goal is given, default to working on the current branch's changes (see step 1) — review what's been written and address what the review finds. Only if the branch has no changes do you fall back to "advance all triaged issues and unaddressed reviews" (GitHub context permitting).
0. Load config and the shared references
python3 "${CLAUDE_PLUGIN_ROOT}/lib/load_config.py"
Then read these two files and follow them:
${CLAUDE_PLUGIN_ROOT}/reference/work-model.md— how to resolve the mode (github vs local) and the I/O contract / ledger for each.${CLAUDE_PLUGIN_ROOT}/reference/workflow.md— how to reason about a request and compose the right workflow (the mission, the decision framework, effort right-sizing, the primitive toolbox, and illustrative patterns).
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 · 229 lines · 217 tokens per session scan A 5b651df60bcd
run is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 217 tokens to every session and 3,264 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
review
5-pass structured code review — correctness, security, performance, readability, consistency.