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/rlaope/nen/agents-mdgit clone --depth 1 https://github.com/rlaope/nenWhat 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 | $0.01637 | $0.01637 |
| Opus 5 | $0.00818 | $0.00818 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
nen 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 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.
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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nen skills — the En protocol
The nen abilities (https://github.com/rlaope/nen): one per Nen category, hatsu (forging new skills) at the center, en — this protocol itself — and vow, the pre-commitments that bind each engagement.
Run En on every incoming task:
- Classify the WORK, not the words. Ask what must be true afterward — a number moved (enhancer), a behavior-preserving change of shape (transmuter), words that land with an audience (emitter), a mechanism named (specialist), survival under failure (conjurer), verified distributed work (manipulator), an ability that doesn't exist yet (hatsu). Never route on keyword overlap; skill descriptions are scent, not the mechanism.
- Engage every skill the work genuinely spans — stacking two or three in dependency order is normal. Read each engaged SKILL.md FIRST, then act.
- Announce the engagement in one line, e.g. "En: specialist -> conjurer".
- Right under the announcement, declare the engagement's vows — up to three falsifiable pledges distilled from the engaged skills' Done means plus up to three scope pledges — and audit every vow before claiming done (the vow ability's SKILL.md holds the discipline).
- "nen off" suspends this protocol; "nen on" resumes it. Acknowledge both.
- If a skill still fires on the wrong problem, its Boundaries section names the sibling to hand off to — follow the hand-off.
- enhancer (skills/enhancer/SKILL.md): Profiling-first performance engineering — baseline, profile, change one thing, re-measure. Use when the user says "slow", "make this faster", "optimize", "profile", "benchmark", or "hot path"; when they report latency problems, p99 spikes, low throughput, memory growth, or N+1 queries; when a request times out under load but works in dev; when someone wants to know why an endpoint takes 800ms; or when a perf change is proposed without a number attached.
- transmuter (skills/transmuter/SKILL.md): Behavior-preserving refactoring under characterization tests, plus severity-rated code review. Use when the user says "refactor", "clean up", "tech debt", "code review", "extract", "rename", "restructure", "this file is a mess", or "impossible to modify"; when every small change breaks something unrelated; when cleanup has to land before the next feature has anywhere to go; when code is called hard to change, scary to touch, or too tangled to test; when requirements shifted and the current shape fights the new feature; when a PR needs review for structure and maintainability; or when every small change keeps ballooning because everything touches everything.
- emitter (skills/emitter/SKILL.md): Launch, positioning, and promotion — making finished work land with the audience that should care. Use when the user says "launch", "announce", "release notes", "changelog", "blog post", "tweet thread", "X thread", "Show HN", "Hacker News post", "how do I promote this", "who would care about this", or "positioning"; when a README needs a pitch instead of a manual; when something is built and working but nobody outside the repo knows it exists; or when launch copy already exists but reads like a feature list.
- specialist (skills/specialist/SKILL.md): Reverse engineering and mechanism-comparison research — when the docs run out, read the artifact itself and prove how the thing actually works. Use when the user asks "how does actually do it", says "reverse engineer this", "undocumented behavior", "the docs don't match what happens", or "the docs never mention it"; when a dependency, vendor SDK, legacy system, or external API behaves in ways nobody on the team can explain; when the ask is to compare implementations of the same mechanism across libraries or competitors; when someone says "we've tried everything" about a black-box system; or when the only source of truth is minified bundles, compiled binaries, or network traffic.
- conjurer (skills/conjurer/SKILL.md): Failure-mode-driven reliability engineering — enumerate how it breaks, give every mode a verdict, prove every handler with a reproducing test. Use when the user says "flaky", "harden this before launch", "what if this fails", "error handling", "timeout", "retry", "idempotency", or "race condition"; when an incident or postmortem lands; when a job crashes halfway and leaves partial state; when a webhook or queue consumer double-fires, sees double delivery, or charges a customer twice; when crash recovery is undefined; or when code is about to ship with only happy-path tests.
- manipulator (skills/manipulator/SKILL.md): Orchestration engineering for multi-agent and deep-research work — decomposition, routing, prompt design, and verified delegation. Use when the user says "plan this", "break this down", "delegate", "orchestrate", "subagent", "task distribution", "parallel workstreams", "split this across agents", "hand this to three agents", "write a prompt for", or "research X thoroughly"; when work must be divided into workstreams that different agents or people can own; when they ask which model or agent should handle something; when work is multi-step and ambiguous enough that one agent charging ahead would guess wrong; when several independent investigations could run in parallel; or when a subagent has reported "done" and someone is about to believe it.
- hatsu (skills/hatsu/SKILL.md): Skill forging — distilling a team's recurring, hard-won practice into a new installable SKILL.md that meets the nen contract. Use when the user says "write a skill", "create a skill for", "turn this workflow into a skill", "codify our process", or "SKILL.md"; when someone says "we keep solving this the same way" or "the team keeps re-teaching this in review"; after a retro where the same lesson surfaces for the second or third time; or when an agent keeps making a mistake that a written discipline would have prevented.
- en (skills/en/SKILL.md): Aura-field auto-routing — read an incoming request's problem shape and engage the right nen abilities, stacked in dependency order when the work spans more than one discipline. Use when the user says "nen", "use nen", "nen mode", "run this through nen", "which skill applies", or "route this"; when a request plausibly spans more than one nen discipline; when you are about to pick a single skill and are not certain it is the right one; or when the user has asked for nen to be the standing baseline for the session.
- vow (skills/vow/SKILL.md): Pre-commitment engineering — declare falsifiable vows before the work starts and audit every one before claiming done, discipline pledges distilled from the engaged skills' Done means plus scope pledges bounding the blast radius. Use when the user says "don't touch anything else", "only this file", "stay in scope", "no new dependencies", "don't tell me it's done until", "commit to your constraints", or "show me the failing test first"; when a previous attempt was declared done and was not; when a diff wandered into files nobody asked about; when en announces an engagement (the announcement is the vow moment); or when delegated work needs acceptance criteria the delegate can be audited against.
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 · 35 lines · 1,637 tokens per session scan A 4df68ac10d11
nen AGENTS.md is an instructions file published in the GitHub repository rlaope/nen (3 stars, last pushed 29d ago), licensed MIT. It adds 1,637 tokens to every session, about $0.0082 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
cortex-mem AGENTS.md
Instructions for sopaco/cortex-mem, covering cortex memory - ai agent context guide, project overview, core concepts, memory dimensions and three-tier layers.
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
agent-skills AGENTS.md
Instructions for sayeed1999/agent-skills, covering agents.md, output style, output style, 1. think before code and 2. simplicity.
webflow-skills AGENTS.md
Instructions for 224-Industries/webflow-skills, covering 224 industries - webflow agent skills repository, agents.md (symlink to claude.md), repo structure, reference file conventions and content style.