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 Amatofrancesco99/thoughtweave --skill init-agents-filegit clone --depth 1 https://github.com/Amatofrancesco99/thoughtweaveWrote 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/amatofrancesco99/thoughtweave/init-agents-file)<a href="https://agentmods.dev/skills/amatofrancesco99/thoughtweave/init-agents-file"><img src="https://agentmods.dev/badge/skills/amatofrancesco99/thoughtweave/init-agents-file/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/amatofrancesco99/thoughtweave/init-agents-file"><img src="https://agentmods.dev/badge/skills/amatofrancesco99/thoughtweave/init-agents-file.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 | $0.00062 | $0.02179 |
| Opus 5 | $0.00031 | $0.01090 |
| Sonnet 5 | $0.00012 | $0.00436 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade A, and why
init-agents-file 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.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/init-agents-file
Generate and maintain a project-specific AGENTS.md file that reflects the actual architecture, constraints and conventions of the project. The generated file must be project-specific, not a generic template.
Pre-condition Check
Before proceeding, the skill must check whether an AGENTS.md already exists in the repository root:
- If
AGENTS.mdalready exists, report its current state (file size, last modified date) and ask the user whether they want to regenerate from scratch, update specific areas, or skip. - Skip exits immediately.
- Regenerate from scratch discards the existing file and runs the full generation flow.
- Update specific areas enters Update Mode where the skill reads the existing file and merges changes.
- If
CLAUDE.mdexists as a regular file (not a symlink), replace it with a symlink pointing toAGENTS.md.
Behaviour
The skill is a tool for the developer, not a replacement. The developer stays at the centre - every question, every decision, every section of AGENTS.md is driven by the developer's answers and intent. The skill does not make assumptions about what the developer wants; it asks.
The core mechanism is a conversational question-and-answer process. The skill asks the user a sequence of questions, one at a time, to progressively define the content of AGENTS.md. Each answer directly shapes what gets written into the file. Throughout this process, surface hidden assumptions as a mandatory concern - document implicit knowledge that the user may not have explicitly stated.
If the repository is empty:
Propose best practices matching the project goal. The interaction should feel like a conversation with an experienced engineer, not like filling out a form.
If the repository already exists:
Inspect the codebase and infer as much context as possible before generating recommendations. This includes:
- repository structure - how the code is organized
- technology stack - languages, frameworks, libraries, build tools
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.
- 9d ago First seen · 166 lines · 62 tokens per session scan A fd9e75ad9f68
init-agents-file is a skill published in the GitHub repository Amatofrancesco99/thoughtweave (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 2,179 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
harness
Route Harness Starter Kit workflows. Use when the user invokes /harness with adopt, doctor, update, refresh, review, or review sub-agent, or asks to apply, diagnose, maintain, or review repository harness guidance.
harness-adopt
Apply Harness Starter Kit prompt-first adoption to a target repository. Use when the user asks to apply, install, adopt, or bootstrap repository harness guidance, checks, memory, and adoption reporting.
harness-review
Review the current change set from an opposing harness-engineering perspective. Use when the user asks for /harness review, /harness review sub-agent, or a no-edit harness review.
harness-update
Refresh an adopted target repository from the latest Harness Starter Kit reference. Use when the user asks for /harness update or wants source tracking and selective harness updates.
harness-doctor
Run the diagnostic Harness Doctor workflow. Use when the user asks for /harness doctor, harness score, repository harness readiness, or a no-edit harness health report.
harness-refresh
Review stale, duplicated, obsolete, or unused target harness guidance. Use when the user asks for /harness refresh or wants harness maintenance recommendations without default edits.