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 AI45Lab/SentrySkills --skill sentryskills-extragit clone --depth 1 https://github.com/AI45Lab/SentrySkillsWrote 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/ai45lab/sentryskills/sentryskills-extra)<a href="https://agentmods.dev/skills/ai45lab/sentryskills/sentryskills-extra"><img src="https://agentmods.dev/badge/skills/ai45lab/sentryskills/sentryskills-extra/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/ai45lab/sentryskills/sentryskills-extra"><img src="https://agentmods.dev/badge/skills/ai45lab/sentryskills/sentryskills-extra.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 | $0.00025 | $0.01368 |
| Opus 5 | $0.00013 | $0.00684 |
| Sonnet 5 | $0.00005 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
sentryskills-extra 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 10d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SentrySkills Extra
Purpose
sentryskills-extra has two distinct responsibilities:
extra_rule: online rule extension afterbase_ruleextra_memory: post-model-stage knowledge management and end-of-task proposal sweeping by the main agent
This skill must not use any framework-external model.
Execution Boundary
extra_rule
extra_rule runs during the online decision path:
- after
base_rule - before
rule_gate - using only active extra rules
It may:
- match active extra rules
- raise the rule-stage decision conservatively
- apply rules by
phase_scope(preflight,runtime,output, orall)
It may not:
- generate candidate rules
- write textual memory
- run dedup or validation
extra_memory
extra_memory runs only after model_stage is completed.
It may:
- synthesize candidate rules from model findings
- store textual memory
- deduplicate similar knowledge
- validate new candidate rules
- promote validated rules into
active_extra_rules.json
For async subagent results:
- the subagent may only write proposal files
- proposal files are swept and consumed by the main agent
- async analysis does not directly modify active or candidate stores
- proposal sweep only affects subsequent turns
It must not run when:
rule_stage_action == blockmodel_stageis skippedmodel_stageis still pending
If the hook reports model_stage_status = rule_proposer_required, a feedback or
outcome signal indicated a possible missed risk. The framework must run a model
rule-proposer pass over pending_rule_proposer_task and call the hook again with
structured model_stage.rule_candidates.
Model-Stage Knowledge Contract
After a completed model_stage, the framework agent must pass reusable knowledge to the runtime hook:
rule_candidates: deterministic extra-rule proposals for patterns that can be checked locallymemory_candidates: natural-language observations for patterns that are useful but not rule-stable
What ships with it
2 files 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.
- 10d ago First seen · 173 lines · 25 tokens per session scan A f5a5ad88b71b
sentryskills-extra is a skill published in the GitHub repository AI45Lab/SentrySkills (9 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,368 once invoked, about $0.0001 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…