mission

mission is a command for Claude Code from samibs/skillfoundry. It costs 132 tokens per session (1,252 once invoked), scanned A, original, MIT.

A governed development workflow that records work, evidence, ownership, and provenance in durable project files. It coordinates implementation, testing, validation, integration, and publishing across agents and worktrees.

In plain words
What is it for?
Use it to plan parallel work, register agents, track evidence, verify clean termination, manage worktree ownership, and prove that contributions were integrated.
Why use it?
It helps detect unverified completion, conflicting writers, hung processes, orphaned servers, and changes that were lost during integration.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Codex.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is git worktree add -b agent/AF-302 ../wt/AF-302 <base-sha>.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote 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.

agentmods badge for mission

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/mission.svg)](https://agentmods.dev/commands/samibs/skillfoundry/mission)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/mission"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/mission.svg" alt="Measured on agentmods" height="20"></a>
Per session 132 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,252 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00132 $0.01252
Opus 5 $0.00066 $0.00626
Sonnet 5 $0.00026 $0.00250
Haiku 4.5 $0.00013 $0.00125

Measured today against content hash 25b88d8245f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 today.

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.

.claude/commands/mission.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/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.

Single-worker flow

/mission init STORY-042 --title "JWT refresh rotation"
/mission attest STORY-042 --worker claude-coder-042 --agent claude --allow-main
/mission gate STORY-042                       # WRITES AUTHORIZED / BLOCKED

# ... implement ...

/mission evidence STORY-042 --kind tests --run "npm test"
/mission ac STORY-042 --file criteria.json
git commit -m "feat(auth): refresh rotation [STORY-042]"
/mission commit STORY-042 --base <base-sha>   # a contribution is usually >1 commit
/mission set STORY-042 implementation_status COMPLETE
/mission set STORY-042 acceptance_status PASS
/mission verify STORY-042
/mission report STORY-042 --out docs/reports/STORY-042.md

Read the full file on GitHub · 111 lines

Changes

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.

  1. today First seen · 111 lines · 132 tokens per session scan A 25b88d8245f3

Subscribe to this mod's changes

mission is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 1,252 once invoked, about $0.0007 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 2026-09-05.