Borrowing it
Nothing to install: this file belongs to ctxpipe-ai/ctxpipe. 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/ctxpipe-ai/ctxpipe/main/.agents/skills/writing-for-agents/SKILL.mdgit clone --depth 1 https://github.com/ctxpipe-ai/ctxpipeWrote 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/ctxpipe-ai/ctxpipe/writing-for-agents)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/writing-for-agents"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/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/ctxpipe-ai/ctxpipe/writing-for-agents"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/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 5.5 | $0.00011 | $0.00940 |
| Sonnet 5.5 | $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 1mo 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
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.
- 1mo ago First seen · 82 lines · 28 tokens per session scan A a842323e664e
writing-for-agents is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 2,351 once invoked, about $0.0001 per session on Opus 5.5. 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
setup-open-index
Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.
edit-brain
How to add or edit knowledge in this brain — define doctypes, add or update entities, and correlate them with relationships. Use whenever the user asks to add/update knowledge, define a concept, record a learning, or link two things in the brain.
bcc-plan-spar
BCC align+lock+review PLAN.md for one slice (no product code). Slash: /bcc-plan-spar · chat: bcc:plan-spar · "lock PLAN" · spar the plan. Args: rounds=N (auto-review cap), review=self|subagent|cli|auto|off. Grill until clear enough (no default Q&A quota). Hand off to bcc-clean-cut after human APPROVE.
bcc-throughline
BCC global progress cockpit (plans.md/progress.md/findings.md). Slash: /bcc-throughline · chat: bcc:throughline · "where are we" · reprioritize · resume after /clear. Not for coding or full PLAN grill.
bcc-breaking-coding-chaos
BCC main skill: dual-loop coding workflow (throughline → plan-spar → clean-cut) or quick status+next. Slash: /bcc-breaking-coding-chaos · chat: bcc:breaking-coding-chaos · "run BCC" · "BCC status" · "what next BCC". Needs a real idea (1:1 implement). Args: goal text, or status. May pass plan-spar review budget as…
bcc-clean-cut
BCC minimal implement from locked PLAN.md (ponytail ladder + verify). Slash: /bcc-clean-cut · chat: bcc:clean-cut · "implement PLAN" after human APPROVE. Not for plan grill (use bcc-plan-spar).