Borrowing it
Nothing to install: this file belongs to yusifeng/formax. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yusifeng/formax/main/.codex/skills/formax-skill-capture/SKILL.mdgit clone --depth 1 https://github.com/yusifeng/formaxWrote 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/yusifeng/formax/formax-skill-capture)<a href="https://agentmods.dev/skills/yusifeng/formax/formax-skill-capture"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-skill-capture/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/yusifeng/formax/formax-skill-capture"><img src="https://agentmods.dev/badge/skills/yusifeng/formax/formax-skill-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 61 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00545 |
| Opus 5 | $0.00032 | $0.00272 |
| Sonnet 5 | $0.00013 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
formax-skill-capture 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 9d 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.
What it actually says
Formax skill capture (create skills from our workflow)
What this is
This skill is a Formax-specific wrapper around skill authoring: it helps us reliably convert “we just figured out how to do X” into a repo-local skill under .codex/skills/<skill-name>/.
It complements the built-in skill-creator (system skill) by adding Formax conventions:
- repo-local skills (checked into git)
- “where to change what” file map
- invariants (UI parity, model injection orthogonality, etc.)
- minimum regression tests to lock behavior
When to use
Trigger this when the user says:
- “把这个流程沉淀成 skill”
- “以后别再忘了怎么改 /xxx”
- “给我一个复用的修改清单/固定套路”
Minimal questions to ask (do not proceed until answered)
- Skill name (kebab-case), e.g.
formax-slash-command-workflow - 1–2 sentence description: when should Codex use it?
- Scope: which subsystem? (pick one)
- slash commands / overlays
- tools (spec/handler/presenter)
- hooks
- permissions/policy
- stability/input routing
- Any explicit “don’t change” constraints? (UI copy/spacing/colors, contracts, etc.)
Output requirements
The resulting skill must include:
- a short “Goal” section
- “Where to change what” (file list)
- “Patterns” (2–4 common patterns)
- “Tests to update” (minimum regression set)
- “Guardrails” (what must not regress)
Avoid long prose; prefer checklists.
Create a new skill (scaffold)
Use the scaffold script:
bash .codex/skills/formax-skill-capture/scripts/new-skill.sh <skill-name> "<description>"
Then fill SKILL.md body with the content above.
Refactor policy for skills
When a skill is created from a workflow we already shipped:
- Do not broaden scope (no extra features)
- Do not rewrite UI (unless explicitly requested)
- Write/extend tests first if behavior has regressed before
What ships with it
1 file 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.
- 9d ago First seen · 65 lines · 63 tokens per session scan A 6e397a539a4d
formax-skill-capture is a skill published in the GitHub repository yusifeng/formax (193 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 545 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
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".