agentmods.dev

using-sentryskills

using-sentryskills is a skill for Claude Code, Codex from AI45Lab/SentrySkills. It costs 36 tokens per session (3,051 once invoked), scanned B, original, MIT.

A required workflow for running SentrySkills, a system that checks task rules and risk before and after model-assisted work. It defines the order of rule checks, risk assessment, optional model review, and follow-up records.

In plain words
What is it for?
Use it as the entry point for tasks that need rule gating, risk checks, model-stage decisions, and end-of-task maintenance proposals.
Why use it?
It provides a fixed review sequence for deciding whether work may continue and for recording rules, risks, and later recommendations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

not rated 9repo 3mo ago B scan 36 tokens original MIT

Good fit Use it as the entry point for tasks that need rule gating, risk checks, model-stage decisions, and end-of-task maintenance proposals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ai45lab/sentryskills/using-sentryskills
View source ↗ AI45Lab/SentrySkills
Install

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.

Any agent
npx skills add AI45Lab/SentrySkills --skill using-sentryskills
Clone the repo
git clone --depth 1 https://github.com/AI45Lab/SentrySkills

Made for: Claude Code, Codex.

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 using-sentryskills

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai45lab/sentryskills/using-sentryskills/github.svg)](https://agentmods.dev/skills/ai45lab/sentryskills/using-sentryskills)
Your own site
<a href="https://agentmods.dev/skills/ai45lab/sentryskills/using-sentryskills"><img src="https://agentmods.dev/badge/skills/ai45lab/sentryskills/using-sentryskills/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.

agentmods 80×15 button for using-sentryskills

Your own site · 80×15
<a href="https://agentmods.dev/skills/ai45lab/sentryskills/using-sentryskills"><img src="https://agentmods.dev/badge/skills/ai45lab/sentryskills/using-sentryskills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00036 $0.03051
Opus 5.5 $0.00014 $0.01220
Sonnet 5.5 $0.00007 $0.00610
Haiku 4.5 $0.00004 $0.00305

Measured 1mo ago against content hash fb1614bfd147, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

using-sentryskills scanned grade B with 1 finding 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

`ignore previous instructions` should normally scope to `preflight,runtime`.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

using-sentryskills/SKILL.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using SentrySkills

Purpose

using-sentryskills is the entry skill. It defines the required execution order for every task:

base_rule -> extra_rule -> rule_gate -> risk assessment -> model_stage -> end-of-task proposal sweep

The first three stages are mandatory and synchronous. model_stage is conditional. Proposal sweep is a main-agent maintenance step that runs at the end of every task and only affects subsequent turns.

Required Behavior

  1. Build the current input payload and run shared/scripts/self_guard_runtime_hook_template.py once for rule gating.
  2. Read the result under .sentryskills/base/.
  3. If rule_stage_action == block, stop and treat that hook result as the final guard result.
  4. If rule_stage_action != block, run the task's model_stage in sync or async mode according to the risk gate.
  5. After a completed model_stage, call the runtime hook again with the completed model-stage knowledge envelope. This second call is what writes extra rules, textual memory, or async proposal files.
  6. Treat preflight, runtime, and output as separate rule -> model stages. Rule results run first; model results may only tighten decisions.
  7. Apply action-level gating to planned actions and dynamic skill actions. If only some actions are risky, downgrade and execute only allowed actions; if all declared actions are blocked, block the task.
  8. During execution, before invoking any non-SentrySkills skill, submit a runtime skill_invocation gate for that specific skill call.
  9. Execute only the actions returned in allowed_actions / allowed_skill_steps; do not execute blocked_actions / blocked_skill_steps.
  10. At task end, if this is a main-agent turn, ensure one proposal sweep has run.
  11. Respect the returned stage fields:
  • base_rule_action
  • extra_rule_action
  • rule_stage_action
  • model_dispatch_mode
  • model_stage_status
  • model_stage_action
  • model_executor
  • model_stage_result_available
  • action_gate
  • skill_gate
  • execution_directive
  • proposal_sweep_effect
  • knowledge_writeback_status
  • final_action

Read the full file on GitHub · 335 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. 1mo ago First seen · 335 lines · 36 tokens per session scan B fb1614bfd147

Subscribe to this mod's changes

using-sentryskills is a skill published in the GitHub repository AI45Lab/SentrySkills (9 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 3,051 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsSecurity
Related

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…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens