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 companion-inc/introspect --skill writing-agent-promptgit clone --depth 1 https://github.com/companion-inc/introspectWrote 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/companion-inc/introspect/writing-agent-prompt)<a href="https://agentmods.dev/skills/companion-inc/introspect/writing-agent-prompt"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/writing-agent-prompt/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/companion-inc/introspect/writing-agent-prompt"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/writing-agent-prompt.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 | $0.00068 | $0.00632 |
| Opus 5 | $0.00034 | $0.00316 |
| Sonnet 5 | $0.00014 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
writing-agent-prompt 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 11d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Agent Prompt
Purpose
Use this skill for prompt wording after agent-md-creator has decided that the behavior belongs in an always-loaded prompt. This skill is about phrasing and behavioral verification, not placement.
Procedure
- Read the failure transcript and name the unwanted model move in one sentence.
- Write the desired first move and final artifact in plain behavioral terms.
- Rewrite the instruction with action verbs such as
produce,implement,continue,substitute,verify, andreport. - Put research requirements inside the action path: the model should discover missing details with tools while moving toward the artifact.
- If a sub-action cannot run, phrase the recovery as substitution and continuation.
- Verify by probing the actual agent with a realistic prompt from the failure and reading the response for behavior. The response should start the work, name the first concrete action, and avoid asking for permission when authorization is already present.
- If the probe fails, revise the prompt and probe again. Do not replace the behavioral test with a text-matching proxy.
Gotchas
- A prompt can match expected words and still fail behaviorally. Judge the response, not isolated text.
- A text-matching proxy can block legitimate prompt text while missing the same failure expressed another way.
- Prefer "answer with the changed artifact and verification" over naming every bad response style.
- A hidden or empty skill folder is not a skill. It needs
SKILL.mdfrontmatter and an index entry so the reflector can route to it. - Do not blindly obey this skill when the edited prompt is for a regulated product workflow; read the product docs and verify the result against the real prompt file.
Verification
- Run at least one behavior probe against the actual agent runtime that loads the edited prompt.
- Run
./scripts/validate-skills.pyafter creating or changing this skill. - For core prompt edits, run
./scripts/introspect-status.shand confirm Claude and Codex prompt links target the edited file.
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.
- 11d ago First seen · 43 lines · 68 tokens per session scan A fe327e9e3154
writing-agent-prompt is a skill published in the GitHub repository companion-inc/introspect (10 stars, last pushed 22d ago), licensed MIT. It adds 68 tokens to every session and 632 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 2026-08-31.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…