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/stainless-code/codemap/writing-great-skillsnpx skills add stainless-code/codemap --skill writing-great-skillsgit clone --depth 1 https://github.com/stainless-code/codemapWrote 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/stainless-code/codemap/writing-great-skills)<a href="https://agentmods.dev/skills/stainless-code/codemap/writing-great-skills"><img src="https://agentmods.dev/badge/skills/stainless-code/codemap/writing-great-skills.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02002 |
| Opus 5 | $0.00012 | $0.01001 |
| Sonnet 5 | $0.00005 | $0.00400 |
| Haiku 4.5 | $0.00002 | $0.00200 |
Grade A, and why
writing-great-skills 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 5d 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.
This is a copy
100% identical to writing-great-skills — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A skill exists to wrangle determinism out of a stochastic system. Predictability — the agent taking the same process every run, not producing the same output — is the root virtue; every lever below serves it.
Bold terms are defined in GLOSSARY.md; look them up there for the full meaning.
Invocation
Two choices, trading different costs:
- A model-invoked skill keeps a description, so the agent can fire it autonomously and other skills can reach it (you can still type its name too). It contributes to context load — the description sits in the window every turn. Mechanics: omit
disable-model-invocation, and write a model-facing description with rich trigger phrasing ("Use when the user wants…, mentions…"). - A user-invoked skill strips the description from the agent's reach: only you, typing its name, can invoke it — and no other skill can. Zero context load, but it spends cognitive load: you are the index that must remember it exists. Mechanics: set
disable-model-invocation: true; thedescriptionbecomes human-facing — a one-line summary, trigger lists stripped.
Pick model-invocation only when the agent must reach the skill on its own, or another skill must. If it only ever fires by hand, make it user-invoked and pay no context load.
When user-invoked skills multiply past what you can remember, that piled-up cognitive load is cured by a router skill: one user-invoked skill that names the others and when to reach for each.
Writing the description
A model-invoked description does two jobs — state what the skill is, and list the branches that should trigger it. Every word increases context load, so a description earns even harder pruning than the body:
- Front-load the skill's leading word — the description is where it does its invocation work.
- One trigger per branch. Synonyms that rename a single branch are duplication — "build features using TDD … asks for test-first development" is one branch written twice. Collapse them; keep only genuinely distinct branches.
- Cut identity that's already in the body. Keep the description to triggers, plus any "when another skill needs…" reach clause.
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.
- 5d ago First seen · 83 lines · 24 tokens per session scan A 7d80554eac9b
writing-great-skills is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,002 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to writing-great-skills, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
release
Publishing a jMunch release (jcodemunch-mcp, jdocmunch-mcp, jdatamunch-mcp, jragmunch-cli), reviewing/merging/closing PRs, and responding to the community. Load before any version bump, PyPI upload, tag, GitHub release, MCP registry publish, or PR merge.
observatory
Context for the jcodemunch-observatory weekly scorecard — what it tracks, the Monday 06:00 UTC cron, why scores must be pulled live rather than transcribed, the NestJS grade story, and the workflow's version dispatch input. Load before quoting, interpreting, or editing observatory scores or config.
benchmark-methodology
Rules for measuring or quoting any benchmark number in this repo. Load before running the bench tier, writing a delta into a PR or CHANGELOG, or touching anything under benchmarks/.
claude-md-budget
How to keep CLAUDE.md under its character Floor without deleting a rule: measure sections first, rotate by derivability, two edits per rotation. Load in /release step 6 and before any CLAUDE.md rotation or split.
pr-description
The PR title and body template, and the rules for any comment drafted for a reporter or contributor. Load when writing a PR body, a release PR, or a triage response.