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 escoffier-labs/skillet --skill pressure-testgit clone --depth 1 https://github.com/escoffier-labs/skilletWrote 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/escoffier-labs/skillet/pressure-test)<a href="https://agentmods.dev/skills/escoffier-labs/skillet/pressure-test"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/pressure-test/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/escoffier-labs/skillet/pressure-test"><img src="https://agentmods.dev/badge/skills/escoffier-labs/skillet/pressure-test.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 | $0.00078 | $0.01424 |
| Opus 5 | $0.00039 | $0.00712 |
| Sonnet 5 | $0.00016 | $0.00285 |
| Haiku 4.5 | $0.00008 | $0.00142 |
Grade A, and why
pressure-test 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pressure-test
The gate between "I have an idea" and "here is a plan." A plan only earns the build when its load-bearing decisions are explicit and its unresolved branches are closed. This skill drives toward that, one decision at a time, and refuses to let a vague idea coast into implementation on momentum.
Two modes, one job. In interactive mode the user answers. In sous mode the user has stepped away and the agent answers in their place, on the record. Either way the deliverable is the same: a set of decisions someone can build from, each one traceable to why it was made.
The mechanic that makes this work
Every decision gets pinned to its basis. That pin is the whole point, it is what separates a real decision from a guess wearing a confident voice.
- In interactive mode, the basis is the user's answer. You propose, they confirm or redirect, you record what they chose.
- In sous mode, you supply the basis and you label it honestly, one of:
evidence(something you inspected this session: the repo, docs, a tool's--help, an upstream project),stated-constraint(the user's own prior decisions or stated limits), orjudgment(your best call, nothing verifiable behind it). A decision built on more than one gets split labels naming the unverified part, like:evidence+judgment (the endpoints are from the load report; the 300ms target is mine).
A raw limit the user stated is stated-constraint; a conclusion you drew from it is judgment. "The ADR forbids new datastores" is stated-constraint; "so reusing the existing Redis is fine" is judgment built on it. Recalled knowledge you could not re-confirm this session is judgment, not evidence. Collapsing these distinctions is the one dishonest move this skill exists to prevent.
How to run it
Work the decisions in dependency order, never as a questionnaire dump. Resolve the upstream decision before the ones that hang off it. Before asking anything, check whether the repo, docs, or files already answer it, an answer you can read is not a question you should ask.
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 · 79 lines · 78 tokens per session scan A c48fc9c482b5
pressure-test is a skill published in the GitHub repository escoffier-labs/skillet (4 stars, last pushed 9d ago), licensed MIT. It adds 78 tokens to every session and 1,424 once invoked, about $0.0004 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
assess-interview-candidate
A structured hiring-assessment workflow that turns a candidate's résumé and a job description into reviewable evidence, interview questions, and an offline HTML report for interviewers.
task-clarifier
Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task…
user-profile-keeper
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration…
run-history-skill-builder
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan. Use when the user asks to make a new skill from real run history, extract a reusable workflow from conversation/logs/files, summarize lessons…
run-history-skill-upgrader
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill. Use when the user asks to improve an existing skill from recent runs, recurring failures, outdated sources, excessive bloat, changed…
session-handoff-prompt
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session. Use when the user asks for a handoff prompt, restart prompt, continuation prompt, context transfer, fresh-session resume, or a compact summary for opening a new session. Do not use for ordinary summaries…