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 agentmods add skills/simota/agent-skills/chiselnpx skills add simota/agent-skills --skill chiselgit clone --depth 1 https://github.com/simota/agent-skillsWhat 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 | $0.00115 | $0.05457 |
| Opus 5 | $0.00057 | $0.02729 |
| Sonnet 5 | $0.00023 | $0.01091 |
| Haiku 4.5 | $0.00012 | $0.00546 |
Grade A, and why
chisel 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 2d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chisel
"A vague word is a decision you left to chance. Carve it into something that can be checked."
Take a prompt as it was written and return it as an executable specification: every expression that admits two defensible readings is either replaced with a bound, a behavior, or a scorable criterion, or is deliberately left open with a recorded reason. Chisel changes the language, never the intent — the source's goal, audience, and constraints are invariants.
Principles: Traceable over fluent · Observable over descriptive · Licensed numbers over invented ones · Capability over title · Open on purpose, never by accident
What ships with it
13 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.
- _common 10 B
- architect 12 B
- nexus 8 B
- oracle 9 B
- reference/_common 13 B
- reference/ambiguity-budget.md 6.7 KB
- reference/ambiguity-lexicon.md 6.9 KB
- reference/architect 15 B
- reference/autorun-schema.md 2.5 KB
- reference/nexus 11 B
- reference/oracle 12 B
- reference/role-decomposition.md 6.8 KB
- reference/translation-patterns.md 8.2 KB
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.
- 2d ago First seen · 277 lines · 115 tokens per session scan A 4e82a48c86d0
chisel is a skill published in the GitHub repository simota/agent-skills (75 stars, last pushed 8d ago), licensed MIT. It adds 115 tokens to every session and 5,457 once invoked, about $0.0006 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
plan
Use when a request needs shaping before any code is written — a rough or vague prompt to sharpen, an ambiguous idea to design, or a clear-enough task to decompose. One chain-starter that amplifies the prompt, designs the approach, and decomposes it into a batched task file, skipping whichever phases the request…
ai-instruction-detox
AI 指令排毒與規則治理：把散落在 CLAUDE.md、AGENTS.md、skills、context、memory 的規則 原子化、查衝突、去重複、找過時、揪 Prompt Injection，產出可套用的精簡架構與回復方案。 觸發時機：用戶說「指令排毒」「規則太亂」「CLAUDE.md 太長」「規則互相矛盾」「上下文減肥」 「AI 設定治理」「多個 Agent 規則分裂」「context 膨脹」，或要求審查／清理 AI 指令檔。 不要觸發：一般程式重構、產品程式碼審查、單純想縮短一份文件（那是編輯不是治理）。.
fellowship
Multi-task orchestrator. Coordinates agent teammates (led by Gandalf) running /quest (code) or /scout (research) workflows. Use when you have multiple independent tasks to run in parallel.
quest
Use for any non-trivial task. Orchestrates the Research-Plan-Implement cycle with compaction between phases, integrating council, lembas, gather-lore, and warden. Enforces discipline and phase gates.
council
Use at the start of any non-trivial task. Loads focused, task-relevant context by reading CLAUDE.md, scanning for related files, and producing a structured Session Context block. Invoked automatically by quest or standalone via /council.
missive
Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.