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/benwu95/prospec/claude-mdgit clone --depth 1 https://github.com/benwu95/prospecWrote 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/benwu95/prospec/claude-md)<a href="https://agentmods.dev/instructions/benwu95/prospec/claude-md"><img src="https://agentmods.dev/badge/instructions/benwu95/prospec/claude-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 | $0.01131 | $0.01131 |
| Opus 5 | $0.00566 | $0.00566 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
prospec CLAUDE.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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prospec
AI-augmented project with Prospec Skills and structured AI Knowledge
Tech Stack
- Language: typescript
- Package Manager: pnpm
Language Policy
The user's primary language for change artifacts (.prospec/changes/**, .prospec/archive/**, prospec/specs/_archived-history/**) is Traditional Chinese (Taiwan), and requests may be phrased in it. The trust zone (prospec/CONSTITUTION.md, prospec/README.md, prospec/index.md, prospec/specs/product.md, prospec/specs/features/**, prospec/ai-knowledge/**) always remains in English, as do code, identifiers, technical terms, and git commit messages — it is technical documentation read next to the code and cited in English, exempt from the Traditional Chinese (Taiwan) requirement. The Constitution's Language Policy rule is generated from this same path set and names the few per-spot exceptions in both directions — trust-zone spots that may use Traditional Chinese (Taiwan), and change-artifact spots that stay English because their content is copied into the trust zone verbatim.
Core Resources
Constitution
Project principles and constraints: prospec/CONSTITUTION.md
AI Knowledge Base
Module index and project structure (L1-L3 navigation): prospec/index.md
Coding Conventions
Coding standards and best practices: prospec/ai-knowledge/_conventions.md
Diagram conventions: prospec/ai-knowledge/_diagram-conventions.md
Project glossary and domain terms: prospec/ai-knowledge/_glossary.md
Available Prospec Skills
Prospec Skills are invoked via /prospec-* slash commands — each skill's description and trigger words are surfaced automatically from its SKILL.md frontmatter, so run the matching /prospec-<name> command to trigger one.
Session Start
At the start of a session, run prospec status — it deterministically reports each in-progress
change's name, current node, suggested next step, and blocking gates (the executable copy of
prospec/ai-knowledge/_status-lifecycle.md). The prospec CLI (version ≥ 1.0.0)
is a required file for the prospec skills: when it is missing or too old, STOP and install/upgrade
the standalone executable before running any skill — never substitute manual steps.
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.
- 3d ago First seen · 63 lines · 1,131 tokens per session scan A a2be5ca719a2
prospec CLAUDE.md is an instructions file published in the GitHub repository benwu95/prospec (5 stars, last pushed 4d ago), licensed MIT. It adds 1,131 tokens to every session, about $0.0057 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
spec_driven_develop CLAUDE.md
Instructions for zhu1090093659/spec_driven_develop: Read AGENTS.md first. It is the shared project-level instruction source for Codex, OpenCode, Cursor, Claude Code, and other Markdown-aware coding agents.
forge CLAUDE.md
Instructions for firatcand/forge, covering forge, stack, commands, conventions and critical paths.
claude-sdd-planner CLAUDE.md
Claude Code instructions for danweinerdev/claude-sdd-planner, covering sdd planner, directory structure, the two-tree architecture, conventions and frontmatter.
claude-sdd-planner AGENTS.md
AGENTS.md instructions for danweinerdev/claude-sdd-planner, covering sdd planner — agent development guide, what this repository is, build and test, editing rules (the ones that bite) and conventions (single sources of truth).
spec-manager CLAUDE.md
Instructions for loki-ai-ch/spec-manager, covering claude.md, spec-driven development — no vibe coding, build & test commands, architecture and source layout.
detach AGENTS.md
AGENTS.md instructions for iltsarev/detach, covering detach agent guide, start here, context and specification policy, context map and verification loop.