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 barlevalon/skills --skill writing-for-agentsgit clone --depth 1 https://github.com/barlevalon/skillsWrote 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/barlevalon/skills/writing-for-agents)<a href="https://agentmods.dev/skills/barlevalon/skills/writing-for-agents"><img src="https://agentmods.dev/badge/skills/barlevalon/skills/writing-for-agents/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/barlevalon/skills/writing-for-agents"><img src="https://agentmods.dev/badge/skills/barlevalon/skills/writing-for-agents.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 | $0.00028 | $0.02351 |
| Opus 5 | $0.00014 | $0.01175 |
| Sonnet 5 | $0.00006 | $0.00470 |
| Haiku 4.5 | $0.00003 | $0.00235 |
Grade A, and why
writing-for-agents 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.
This is a copy
95% identical to writing-for-agents — 50 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference for writing any document an agent consumes — a skill, an AGENTS.md / CLAUDE.md, a doc reached by a pointer. The packaging differs; the writing does not: the same levers make each one predictable — the agent taking the same process every run, not producing the same output.
When the document you're writing is a skill, read SKILL-MECHANICS.md for frontmatter, invocation choice, and router skills.
Context pointers
A context pointer is a reference held in the agent's context that names some out-of-context material and encodes the condition for reaching it. A skill's description is one; a line in AGENTS.md naming a doc is the same object. The pointer's wording, not its target, decides when the agent reaches the material — and how reliably. A must-have target behind a weakly worded pointer is a variance bug: sharpen the wording first, and inline the material only if sharpening fails.
A pointer does two jobs — state what the material is, and list the branches that should trigger reaching it (a branch is a distinct case the document handles, so different runs take different paths through it). Every word of an always-loaded pointer costs on every turn, so it earns even harder pruning than the body:
- Front-load the leading word — the pointer is where it does its triggering work.
- One trigger per branch. Synonyms that rename a single branch are one branch written twice; collapse them and keep only genuinely distinct branches.
- Cut identity the body already carries.
The two loads
Every document and pointer you add spends one of two budgets:
- Context load — the cost of always-loaded material on the agent's window: an
AGENTS.mdline, a skill description, anything sitting in context every turn, spending tokens and attention whether or not it fires. - Cognitive load — the cost on the human: which documents exist and when to reach for each. The human is the index. Not a cost to minimise — it is the price of human agency; spend it where human judgement matters, remove it where it does not.
What ships with it
3 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.
- 9d ago First seen · 82 lines · 28 tokens per session scan A a842323e664e
writing-for-agents is a skill published in the GitHub repository barlevalon/skills (4 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 2,351 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to writing-for-agents, differing in 50 lines, and is treated as a copy.
Other skills, from other repositories
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
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".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
summarize
A guide for turning conversations, logs, documents, or investigation notes into short, action-oriented summaries. It requires conclusions to be tied to available evidence and distinguishes confirmed facts from items still needing confirmation.
pre-modification-check
Use before modifying, refactoring, moving, or deleting files in a Repowise-indexed repository, especially shared utilities, core modules, public APIs, or files the user did not explicitly identify.