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 pincerhq/pincer --skill skill-authoringgit clone --depth 1 https://github.com/pincerhq/pincerWrote 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/pincerhq/pincer/skill-authoring)<a href="https://agentmods.dev/skills/pincerhq/pincer/skill-authoring"><img src="https://agentmods.dev/badge/skills/pincerhq/pincer/skill-authoring/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/pincerhq/pincer/skill-authoring"><img src="https://agentmods.dev/badge/skills/pincerhq/pincer/skill-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00058 | $0.00717 |
| Opus 5 | $0.00029 | $0.00358 |
| Sonnet 5 | $0.00012 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
Authoring a Pincer skill 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring a Pincer skill
A skill is a directory containing a single SKILL.md file. Nothing else is
required — a directory with SKILL.md present is a skill.
skills/<skill-name>/
SKILL.md # required: frontmatter + instructions
reference.md # optional: extra docs, loaded on demand
scripts/
do_thing.py # optional: executable helper
SKILL.md format
---
name: my-skill
description: One dense sentence describing what this skill does and when to use it.
---
# My Skill
Free-form markdown instructions for the agent. This is the body that
`load_skill(name)` returns.
Two frontmatter fields are required: name and description. The
description is the only part shown to the model before it decides to
load the skill (progressive disclosure level 1 — it's injected into the
system prompt's "Available Skills" block), so write it as a dense,
specific sentence that makes clear both what the skill does and when to
reach for it. Vague descriptions ("Helps with stuff") mean the model will
never load the skill.
Progressive disclosure — the three levels
- Level 1 (always in context): name + description only, via the system prompt's Available Skills block.
- Level 2 (
load_skill(name)): returns the full markdown body plus a manifest of any other files in the skill's directory. - Level 3 (
load_skill_reference(name, path)): reads one specific file from the skill's directory by relative path — use this for large reference docs, data files, or examples you don't want in everyload_skillcall.
Adding a script
If the skill needs to do something rather than just explain, add an
executable file (Python or any script with a shebang) anywhere under the
skill's directory and call it with run_skill_script(name, script, args).
Scripts run in a sandboxed subprocess (resource limits + network domain
allowlisting) unless skill_sandbox_disabled is set, and always require
user approval before executing.
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 · 74 lines · 58 tokens per session scan A a0b4951a4ba9
Authoring a Pincer skill is a skill published in the GitHub repository pincerhq/pincer (50 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 717 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 2026-08-30.
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…