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 regen-coordination/org-os-template --skill csis-reviewgit clone --depth 1 https://github.com/regen-coordination/org-os-templateWrote 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/regen-coordination/org-os-template/csis-review)<a href="https://agentmods.dev/skills/regen-coordination/org-os-template/csis-review"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/csis-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/regen-coordination/org-os-template/csis-review"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/csis-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 | $0.00051 | $0.00969 |
| Opus 5 | $0.00026 | $0.00485 |
| Sonnet 5 | $0.00010 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
csis-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 12d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
csis-review
The active counterpart to the static schemas. CSIS-informed, not CSIS-conformant (R7): this skill flags for human/CSIS-literate review — it does NOT issue conformance verdicts. See process/csis-safeguards.md.
What it checks
- Three-level grading. Classify each structural statement as Level 1 (principle), Level 2 (review prompt), or Level 3 (enforceable standard). Don't treat a principle as if it were enforceable.
- Visibility → falsifiability. For a deployment: are its conditions precise enough that an independent reviewer could detect satisfaction or violation from available evidence? If not, flag "visibility substituted for falsifiability" (Durgadas's headline critique).
- Minimum enforceable safeguards (the 7): source/evidence status · AI-synthesis status (marked until reviewed) · resource review status · link status · source-system care · deployment review-readiness (the 6 components — use
checkDeploymentValidity) · implementation-learning boundary (case ≠ pattern). - Overclaim scan. Regeneration/impact/governance/structural-soundness claims that exceed their evidence or
maturity/public_usestate. Apply frame-language discipline (watch Frame-1 extractive language masquerading as regenerative). - Public-use + consent. High-risk content carries a
public-use-boundary; person-nodes/Indigenous-knowledge/exact-locations get consent review.
Output
A review report: per-item findings with a recommended handling mode (cited-reference / review-prompt / native-adaptation / adopted-standard) and a route to the right reviewer (source / domain / structural / community / ecological-MRV / governance / legal / AI / privacy). Flags, not verdicts — escalate to a human reviewer (and, for CSIS constructs, to a CSIS-literate reviewer).
Guardrail
Until the open CSIS decisions resolve, do not assert conformance. Draft-and-present any public-facing output.
Mode: frame-language-audit
Grounding (2026-07-02 planning call, paraphrased — the exact wording comes from a noisy auto-transcription and is not verified for public quoting; see the KB's claim-evidence record + its public-use-boundary companion before citing): Frame-1 terms can make a thing structurally not regenerative — the point is structural, not semantic; where intention and structure diverge, structure beats intention. This mode audits language as structure, per CSIS's informed-not-conformant posture (R7). Cite the published CSIS/Craft standards (and the AI Precision Toolkit once released) rather than call transcripts.
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.
- 12d ago First seen · 58 lines · 51 tokens per session scan A 87aa6d636af9
csis-review is a skill published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 969 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…