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/benedict-armstrong/presio/agents-mdgit clone --depth 1 https://github.com/benedict-armstrong/presioWrote 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/benedict-armstrong/presio/agents-md)<a href="https://agentmods.dev/instructions/benedict-armstrong/presio/agents-md"><img src="https://agentmods.dev/badge/instructions/benedict-armstrong/presio/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 | $0.00399 | $0.00399 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
presio 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 5d 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
AGENTS.md
Coding agents working in this repository.
Project
Presio — PDF presentation app (local-by-default + optional online sync).
client/— Vite + React SPAserver/— Express + Socket.IO + Supabaseschema/— JSON schemas for sidecar formats
Agent-facing product APIs (runtime)
These are served live by the Express app (not static files):
| Path | Purpose |
|---|---|
/llms.txt |
Agent index |
/llms-full.txt |
Present + check playbook |
/AGENTS.md |
Product agent brief |
/api.md / /openapi.json |
API docs |
/robots.txt / /sitemap.xml |
Crawl discovery |
/.well-known/mcp.json / /mcp |
MCP tools present_pdf, check_pdf |
POST /api/present |
Upload PDF → local handoff URL (update in place with session_id + controller token) |
POST /api/check |
Sidecar validity report |
Sources: server/agent/content/, server/routes/agentDocs.ts, server/routes/mcp.ts, server/lib/presentHandoff.ts.
Dev
cd server && npm run dev # API (needs env / Supabase)
cd client && npm run dev # SPA
PRESIO_MODE=local npm run dev runs the API against a bundled SQLite +
filesystem backend instead (server/local/), needing no env at all — no
Supabase, no auth. See deploy/README.md and local.docker-compose.yml.
Conventions
- Prefer local presentations (IndexedDB); server upload only for sync/claim/handoff
- Do not add tests unless asked
- Keep changes focused; match existing style
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.
- 5d ago First seen · 46 lines · 399 tokens per session scan A 86d76e84a595
presio AGENTS.md is an instructions file published in the GitHub repository benedict-armstrong/presio (22 stars, last pushed 3d ago), licensed MIT. It adds 399 tokens to every session, about $0.0020 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 2026-08-30.
Other instructions, from other repositories
academic-writing-skills CLAUDE.md
Claude Code instructions for bahayonghang/academic-writing-skills, covering claude.md, project overview, build & development commands, architecture and skill layout convention.
academic-writing-skills AGENTS.md
AGENTS.md instructions for bahayonghang/academic-writing-skills, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
academic-writing-skills copilot-instructions.md
Copilot instructions for bahayonghang/academic-writing-skills, covering copilot instructions (academic-writing-skills), big picture, key directories, repo-specific rules (do not break) and common workflows.
terminal-browser AGENTS.md
AGENTS.md instructions for zenbu-labs/terminal-browser, a project described as: A browser inside your terminal.
inspector AGENTS.md
AGENTS.md instructions for modelcontextprotocol/inspector, covering inspector v2, skills index, project structure, development setup and dependency placement.
dile-components AGENTS.md
AGENTS.md instructions for Polydile/dile-components, covering development guidelines for dile components, repository overview, packages, documentation site and demos.