Borrowing it
Nothing to install: this file belongs to cmj-hub/claude-psp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cmj-hub/claude-psp/main/AGENTS.mdgit clone --depth 1 https://github.com/cmj-hub/claude-pspWrote 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/cmj-hub/claude-psp/agents-md)<a href="https://agentmods.dev/instructions/cmj-hub/claude-psp/agents-md"><img src="https://agentmods.dev/badge/instructions/cmj-hub/claude-psp/agents-md/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/instructions/cmj-hub/claude-psp/agents-md"><img src="https://agentmods.dev/badge/instructions/cmj-hub/claude-psp/agents-md.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 | $0.00931 | $0.00931 |
| Opus 5.5 | $0.00372 | $0.00372 |
| Sonnet 5.5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
claude-psp 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 10d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Behavior rules for claude-psp
Identity layering
| File | Job | Owner |
|---|---|---|
skills/psp/SKILL.md + skills/psp/modes/ |
JMC FRAMEWORK (5-component PSP), one skill with modes | JMC (do not edit) |
SOUL.md |
Operator's perspective on their buyer | You |
brand-config.json |
ICP precision + PSP drafts + published psp block + signal sources |
You (shared with every pack in the suite) |
Rules
- Always load brand-config.json + SOUL.md first. Missing either → run the
setupmode (skills/psp/modes/setup.md), unless the operator's request carries the seller facts itself: then work from those and offer setup afterward. - Refuse abstract pain. Force the 11am-Tuesday operational moment. If the operator says "they need better demand gen", push back.
- No demographics as signals. "VP of Marketing at Series B SaaS" is not a signal. Quote what they DID.
- No fabricated signals. If a candidate signal can't be sourced publicly, don't include it.
- Pain language must come from the operator's vocabulary list. Refuse to substitute category jargon.
- Time-anchor every PSP. Without a 90-day trigger (new-exec / budget-cycle / obvious-failure), the PSP isn't operational.
- Felt-pain role ≠ buying authority. Push the operator to name who FEELS the pain at 11am Tuesday.
- Stale signals get flagged. Signals >30 days old should not be in active outreach lists.
- Score before you hand off. Run
scripts/score_psp.pyon every PSP and show the operator each flag. Exit 1 (under 70, a stale signal, or a pain that uses none of the buyer's vocabulary phrases) means it isn't operational yet. - Merge, never overwrite.
brand-config.jsonandSOUL.mdare shared by every pack in the suite. Read the existing file, add or update only this pack's fields (psp_drafts,psp,signal_sources,research_cadence), and leave every other key exactly as it was. Never rewrite the file from the example, never delete another pack's keys. Show the diff and ask before changing a field that already has a value.operatorandicpare shared: fill gaps only. InSOUL.md, touch only this pack's own##sections. - Publish the locked primary. When the operator locks a primary PSP that the scorer passes, write the
pspblock:signal_anchors(psp_drafts.primary.signalfirst),primary_pain,timing_trigger,felt_pain_role,vocabulary. Downstream packs (evp, prospect-list, cold-email, pricing, geo, email-sequence) readpsp, not the drafts.
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.
- 10d ago Changed · +1 lines · +61 tokens per session 69e612a441ba
- 24d ago Changed · +9 lines · +412 tokens per session d3250d3bbe67
- 25d ago Changed · +1 lines · +48 tokens per session ba10cbe22faf
- 2mo ago First seen · 33 lines · 410 tokens per session scan A ac9f5b2fe09e
claude-psp AGENTS.md is an instructions file published in the GitHub repository cmj-hub/claude-psp (3 stars, last pushed 2d ago), licensed MIT. It adds 931 tokens to every session, about $0.0037 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.