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/xiaolai/nlpm/agents-mdgit clone --depth 1 https://github.com/xiaolai/nlpmWhat 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 | $0.07846 | $0.07846 |
| Opus 5 | $0.03923 | $0.03923 |
| Sonnet 5 | $0.01569 | $0.01569 |
| Haiku 4.5 | $0.00785 | $0.00785 |
Grade A, and why
nlpm AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. Pattern-matches against Critical/High risk signatures (eval, curl-pipe-sh, credential exfil, etc.) How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
nlpm
nlpm
Natural-Language Programming Manager — multi-tool (Claude Code, Codex CLI, Antigravity) NL artifact scoring, checking, fixing, and testing. Delivered as a Claude Code plugin; the scoring rubric covers all three ecosystems via tier-aware overlays (see analysis/multi-tool-design-2026-05.md).
Architecture
Commands orchestrate agents. Agents use skills as reference knowledge.
Each command does one thing -- no flags (except --changed on score).
Commands
- commands/ls.md --
/nlpm:ls-- discover NL artifacts (dispatches scanner) - commands/score.md --
/nlpm:score-- 100-point quality scoring (dispatches scorer + vague-scanner in parallel) - commands/check.md --
/nlpm:check-- cross-artifact consistency (dispatches checker) - commands/fix.md --
/nlpm:fix-- auto-fix mechanical findings (dispatches scorer) - commands/trend.md --
/nlpm:trend-- track score history over time (dispatches scorer + vague-scanner) - commands/test.md --
/nlpm:test-- run NL-TDD specs (dispatches tester) - commands/init.md --
/nlpm:init-- init project - commands/security-scan.md --
/nlpm:security-scan-- scan plugin for security risks in executable artifacts - commands/vocab-init.md --
/nlpm:vocab-init-- init a vocabulary skill for any project (runs extractor, seeds canonical noun/verb tables, writes R51 opt-in stub). Adopter-facing entry point for vocabulary discipline. - commands/vocab-drift.md --
/nlpm:vocab-drift-- registry-free vocabulary drift scan (dispatches vocab-drift-scanner). Advisory only; no penalty. Use before/alongside R51. - commands/report.md --
/nlpm:report-- self-contained HTML report (per-file scores, trend, cross-artifact graph, vocabulary noun-verb map via AntV G6, drift candidates, findings). Output:.claude/nlpm-reports/index.html. file://-openable, no server. - commands/spec-sync.md --
/nlpm:spec-sync-- sync the tool overlays (conventions-claude/codex/antigravity) with upstream official specs (dispatches spec-researcher per tool in parallel; applies corrections, propagates for self-consistency, verifies via bin/nlpm-check). Never commits/pushes. - commands/shared/discover.md -- artifact discovery patterns (not user-invocable)
- commands/shared/classify.md -- artifact type classification (not user-invocable)
- commands/shared/append-history.md -- snapshot persistence to .claude/nlpm-history.json with scope marker (not user-invocable). Used by /nlpm:init, /nlpm:score, /nlpm:trend so trend data accumulates without manual upkeep.
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 · 358 lines · 7,846 tokens per session scan A d585dca477b4
nlpm AGENTS.md is an instructions file published in the GitHub repository xiaolai/nlpm (133 stars, last pushed 3d ago), licensed ISC. It adds 7,846 tokens to every session, about $0.0392 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.