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/perseus-computing-llc/slack-perseus-agent/agents-mdgit clone --depth 1 https://github.com/Perseus-Computing-LLC/slack-perseus-agentWrote 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/perseus-computing-llc/slack-perseus-agent/agents-md)<a href="https://agentmods.dev/instructions/perseus-computing-llc/slack-perseus-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/perseus-computing-llc/slack-perseus-agent/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 | $0.00474 | $0.00474 |
| Opus 5 | $0.00237 | $0.00237 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
slack-perseus-agent 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 4d 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
Project Context — Perseus for Slack
What this is
A Slack agent that connects developer teams to live project context via MCP. Built for the Slack Agent Builder Challenge 2026 (New Slack Agent track, $42K prize pool, July 13 deadline).
How it works
Slack user → Slack Bolt (Python, Socket Mode) → Perseus MCP server (JSON-RPC 2.0 over HTTP) → workspace/memory backends → formatted Slack Blocks response.
Key files
src/app.py— Slack Bolt app entry pointsrc/mcp_client.py— JSON-RPC MCP client for Perseussrc/handlers.py— Intent routing (services, memory, search, read, onboard, ask)src/blocks.py— Slack Block Kit formatters
Build rules
- Use
syncnot async unless existing async infrastructure - Prefer Slack Blocks over plain text for all responses
- Every MCP call should have a fallback error block
- Intent routing is regex-based; NL fallback uses memory recall
- Demo is a terminal HTML simulation → Playwright → MP4
Hackathon resources
- Devpost: https://slackhack.devpost.com/
- Deadline: July 13, 2026 5pm PT
- Track: New Slack Agent (MCP server integration)
- Prize: $42,000 + Dreamforce trip
- Requirements: ~3 min demo video, architecture diagram, Slack sandbox URL, GitHub repo
Repo
- GitHub: https://github.com/Perseus-Computing-LLC/slack-perseus-agent
- License: MIT
- Owner: Perseus Computing LLC
Perseus MCP tools used
perseus_services— service healthperseus_memory— Perseus Vault recallperseus_mimir— direct FTS5 memoryperseus_read— file inspectionperseus_list— directory enumeration (also powers client-side code search)perseus_skills— skill listingperseus_context— workspace contextperseus_session— session historyperseus_inbox— messages
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.
- 4d ago First seen · 44 lines · 474 tokens per session scan A e17f8654670d
slack-perseus-agent AGENTS.md is an instructions file published in the GitHub repository Perseus-Computing-LLC/slack-perseus-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 474 tokens to every session, about $0.0024 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
fadlie CLAUDE.md
Claude Code instructions for benewende-dev/fadlie, covering fadlie — notes de travail, le problème, mesuré sur le vrai graphe, où est vraiment le trou (mesurer-jumeaux.py), ce qui est vérifié (ne pas re-supposer) and le juge (mesurer-le-juge.py).
Bags-SDK-hackathon CLAUDE.md
Instructions for outerheaven199X/Bags-SDK-hackathon, covering bags hackathon — token launch assistant, auto-scan trigger (critical — always follow), when the user already has a topic, scout launch flow (localhost — no exceptions) and hard rules for launches.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.