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 skills add sumo91/mission-brief --skill mission-reviewgit clone --depth 1 https://github.com/sumo91/mission-briefWrote 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/sumo91/mission-brief/mission-review)<a href="https://agentmods.dev/skills/sumo91/mission-brief/mission-review"><img src="https://agentmods.dev/badge/skills/sumo91/mission-brief/mission-review/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/sumo91/mission-brief/mission-review"><img src="https://agentmods.dev/badge/skills/sumo91/mission-brief/mission-review.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 | $0.00021 | $0.01194 |
| Opus 5.5 | $0.00008 | $0.00478 |
| Sonnet 5.5 | $0.00004 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
mission-review 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission Review
Use outcome review: test the delivered result, not whether the implementation or report resembles the words used to commission it.
Review a completed Mission from its adopted contract, finished artifacts, and available evidence. Keep optional improvements outside failure conditions. Preserve the verdict before entering any separately authorized repair phase; a review-only request leaves the work and contract unchanged.
1. Recover the promise
Locate the Mission Brief or the latest authorized contract that serves the same purpose. Read applicable repository authority, labeled context sources, and only enough implementation record to find the result and its evidence.
Recover:
- the outcome that should now be true for a user or system;
- plausible failures that the contract distinguishes from success;
- required proof and hard boundaries;
- any commission-specific authority or explicit human decision.
Treat Authority Sources, Reference Sources, plans, progress logs, implementation choices, acceptance claims, and earlier proposals according to their actual status. They may preserve context or point to evidence; retention, linkage, or package membership does not silently redefine the Mission.
Preserve meaning rather than sentence form. A wording difference matters only when it changes the promised result, proof burden, boundary, scope, relationship, or authority.
When no reliable contract can be recovered, request the smallest missing decision if it is available from the user. Otherwise review what can be established and keep the verdict INCONCLUSIVE rather than inventing policy.
This step is complete when the promised result and the facts that would materially falsify it can be stated without relying on the implementation's own completion claim.
2. Exercise the finished result
Identify the contract and artifact state being reviewed, using a commit, relevant file digest, deployment identity, or observable state appropriate to the claim. HEAD alone does not identify uncommitted changes. If the result changes during review, identify affected claims and recheck them; qualify a verdict that covers only the earlier state.
What ships with it
1 file 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.
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 Changed · +2 lines 015f0ab79c7e
- 1mo ago Changed · -1 lines b7563edb6550
- 2mo ago First seen · 79 lines · 21 tokens per session scan A de1c5f55dad8
mission-review is a skill published in the GitHub repository sumo91/mission-brief (15 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 1,194 once invoked, about $0.0001 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…