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 Snowflake-Labs/cocoplus --skill sentinelgit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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/snowflake-labs/cocoplus/sentinel)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/sentinel"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/sentinel/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/snowflake-labs/cocoplus/sentinel"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/sentinel.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 | $0.00063 | $0.02220 |
| Opus 5.5 | $0.00025 | $0.00888 |
| Sonnet 5.5 | $0.00013 | $0.00444 |
| Haiku 4.5 | $0.00006 | $0.00222 |
Grade A, and why
sentinel 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
You are executing CocoSentinel — the artifact quality gate. Your task is to evaluate a single artifact across eight dimensions in parallel and produce an overall APPROVED / CONDITIONAL / BLOCKED verdict.
Override rule: Dimension H (Clean Code) FAIL overrides all other dimension outcomes to BLOCKED, regardless of A1–F verdicts.
Before proceeding, verify that .cocoplus/ exists in the current directory. If it does not, output: "CocoPlus is not initialized in this directory. Run $pod init to set up the CocoPlus project bundle and try again." Then stop.
Step 1 — Parse Input
The developer invoked $sentinel <file> where <file> is the artifact path. If no file was provided, ask: "Which file should CocoSentinel evaluate? Provide the file path."
Read the artifact file. If it does not exist, output: "File not found: . Verify the path and try again." Then stop.
Step 2 — Compute SHA-256 Hash
Compute the SHA-256 hash of the artifact's full content. Record it as artifact_sha. This is the evaluation anchor.
Check .cocoplus/sentinel/approvals.jsonl (if it exists) for an existing approval record matching this artifact_sha. If found:
- Surface: "CocoSentinel: an existing approval exists for this artifact (SHA: , approved , outcome: ). Re-evaluate or accept existing approval? Type REEVAL to re-evaluate, or ACCEPT to use existing approval."
- If ACCEPT: display the existing approval summary and stop.
- If REEVAL: proceed with full evaluation.
Create .cocoplus/sentinel/ directory if it does not exist.
Step 3 — Load CocoWisdom Context
Read .cocoplus/wisdom/rejections.jsonl if it exists. For each dimension (A1, A2, B, C, D, E, F), extract the two most recent BLOCKED records where gate: "sentinel" and dimension matches. These become prior_rejection_context for the corresponding dimension agent.
If rejections.jsonl does not exist or has no sentinel records, prior_rejection_context is empty for all dimensions.
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 · 223 lines · 63 tokens per session scan A 1c7565771d62
sentinel is a skill published in the GitHub repository Snowflake-Labs/cocoplus (726 stars, last pushed 21d ago), licensed MIT. It adds 63 tokens to every session and 2,220 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
resolve-drive-pr
Drive an open PR through Polly/OCR, validation, and maintainer handoff.
resolve-review-pr
Review an existing fix PR using the audited repro and full diff, preserving branch and approval rules.
describe-pr
Only use when the user explicitly invokes this skill by name.
otto-impact-assessment
Check the final diff's consumers, focused tests, evidence, and gaps.
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.