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 instructions/wulfgardr/work-assistant/agents-mdgit clone --depth 1 https://github.com/Wulfgardr/work-assistantWrote 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/instructions/wulfgardr/work-assistant/agents-md)<a href="https://agentmods.dev/instructions/wulfgardr/work-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/wulfgardr/work-assistant/agents-md.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 | $0.00218 | $0.00218 |
| Opus 5 | $0.00109 | $0.00109 |
| Sonnet 5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
work-assistant AGENTS.md 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 2d 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.
What it actually says
Istruzioni per chi contribuisce con un agente
- Mantieni il core pubblico indipendente dal provider. Inserisci il comportamento specifico negli adapter.
- Usa solo identità, messaggi e allegati sintetici in codice, test, screenshot e documentazione.
- Non registrare in Git credenziali, file HAR, cookie, token, esportazioni delle caselle o database operativi.
- Mantieni separate ispezione, scrittura locale, bozza sul provider e invio.
- Il core pubblico non deve esporre uno strumento di invio.
- Tratta la vista di conoscenza come dato derivato, non come fonte originale o backup verificato.
- Gli agenti collegati a modelli cloud devono usare il gateway MCP attraverso il broker.
- Mantieni la cartella dati del broker fuori dal workspace leggibile dall'agente.
- Chiama la funzione pseudonimizzazione reversibile, non anonimizzazione.
- Prima di un commit esegui
pytest,python scripts/privacy_check.pye il validatore della skill.
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.
- 2d ago First seen · 13 lines · 218 tokens per session scan A ad982efd4384
work-assistant AGENTS.md is an instructions file published in the GitHub repository Wulfgardr/work-assistant (0 stars, last pushed 10d ago), licensed MIT. It adds 218 tokens to every session, about $0.0011 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 instructions, from other repositories
anytype-ts AGENTS.md
AGENTS.md instructions for anyproto/anytype-ts, covering agents.md, project structure, state management with mobx, electron integration and inter-process communication (ipc).
openquack AGENTS.md
Instructions for larryxiao/openquack, covering agents.md, posture, before you start, workflow and pr template (the required shape).
intentKeeper CLAUDE.md
Instructions for Olawoyin007/intentKeeper, covering claude.md, project overview, development commands, install with dev dependencies and start the classification server.
proton-mail-bridge-client AGENTS.md
Instructions for googlarz/proton-mail-bridge-client, covering memory context and claude-mem status.
macparakeet AGENTS.md
AGENTS.md instructions for moona3k/macparakeet, covering agents.md -- macparakeet, project shape, commands, worktrees and code boundaries.
erga-mcp AGENTS.md
Instructions for Adr1an04/erga-mcp, covering erga mcp contributor and agent guide, start here, product boundary, change routing and privacy and safety.