Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/samibs/skillfoundrynpx agentmods add skills/samibs/skillfoundry/missionWrote 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/samibs/skillfoundry/mission)<a href="https://agentmods.dev/skills/samibs/skillfoundry/mission"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/mission/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/samibs/skillfoundry/mission"><img src="https://agentmods.dev/badge/skills/samibs/skillfoundry/mission.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 | $0.01272 |
| Opus 5.5 | $0.00004 | $0.00509 |
| Sonnet 5.5 | $0.00002 | $0.00254 |
| Haiku 4.5 | $0.00001 | $0.00127 |
Grade A, and why
mission 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 14d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: "Use when work must be provably done, not just finished: governed missions with a durable .ai/ ledger, worker attestation, evidence-gated status, provenance, collision-aware wave planning, agent registry, and process ownership. Triggers: parallel or multi-agent execution, 'is this actually integrated?', 'prove the tests passed cleanly', publishing to a shared branch, reconstructing state after context loss, orphaned dev servers, 'probably pre-existing' claims. Do NOT use for: a single trivial edit (just make it), running quality gates on a diff (use /verify), or building a feature from a PRD (use /forge)."
/mission — Governed Development Mission Protocol
Implement → Test → Iterate → Validate → Evidence → Integrate → Publish
Full protocol:
MULTI_AGENT_PROTOCOL.md· Agent module:agents/_governed-mission-protocol.md
A change is not complete because it compiles, tests locally, or has a commit. Completion requires traceability, evidence, provenance, clean termination, and acceptance.
/mission writes machine-readable artifacts under .ai/ that outlive the agent that produced
them. You do not hand-write that JSON — the CLI writes and validates it, and refuses claims
the repository cannot substantiate.
What it prevents
| Failure | How /mission blocks it |
|---|---|
| Two agents writing in one directory | Registration refuses a second ACTIVE write agent per worktree. |
| A "worktree" that is really a copied folder | Verified against git worktree list --porcelain. |
| "Tests pass" while the runner hung | normal_termination and orphan detection; reported NOT CLEAN. |
| A dev server orphaned after the run | Ownership registry + identity-verified targeted cleanup. |
| A contribution silently dropped in a merge | Provenance: LOST/UNKNOWN block acceptance. Pass --base so a multi-commit contribution is verified as one range. |
| "Pushed" ≠ published | publish-check re-reads the remote SHA, tree and content. |
| "Probably pre-existing" | Requires a baseline run at the accepted SHA, or it is not substantiated. |
| Retry loops burning budget | NO_PROGRESS after two identical failures with no state change. |
| A ledger that drifts from reality | /mission reconcile — the ledger is corrected, never reality. |
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.
- 14d ago First seen · 117 lines · 10 tokens per session scan A d096a004601b
mission is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 14d ago), licensed MIT. It adds 10 tokens to every session and 1,272 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 2026-10-03.
Other skills, from other repositories
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
ring:dispatching-workflows
Executing a phased plan in rolling waves where each phase runs as one multi-agent workflow harness: the supervisor elaborates the phase into tasks against the real landed code, launches a workflow that implements with TDD and runs mandatory in-harness review plus an adversarial contrarian pass (and researchers when…
ring:implementing-tasks
Implementing a single planned task (Task N.M.T) end-to-end: selects the right backend agent by language and service type, drives one TDD RED->GREEN turn, then verifies coverage, lint, license headers, runtime, and delivery before handoff. Runs as Gate 0 before ring:reviewing-code. Use to drive ONE task inside an…
ring:managing-dev-cycle
Managing an in-progress development cycle without driving it: status reports phase, epic/gate progress, assertiveness, and elapsed time from current-cycle.json; cancel confirms, marks the cycle cancelled, and writes a partial feedback report. Use when checking the status of, or cancelling, a running dev cycle. Skip…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…