Borrowing it
Nothing to install: this file belongs to dungnotnull/hybrid-harness-chaos-process-prm. 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/dungnotnull/hybrid-harness-chaos-process-prm/main/CLAUDE.mdgit clone --depth 1 https://github.com/dungnotnull/hybrid-harness-chaos-process-prmWrote 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/dungnotnull/hybrid-harness-chaos-process-prm/claude-md)<a href="https://agentmods.dev/instructions/dungnotnull/hybrid-harness-chaos-process-prm/claude-md"><img src="https://agentmods.dev/badge/instructions/dungnotnull/hybrid-harness-chaos-process-prm/claude-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/dungnotnull/hybrid-harness-chaos-process-prm/claude-md"><img src="https://agentmods.dev/badge/instructions/dungnotnull/hybrid-harness-chaos-process-prm/claude-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 | $0.04421 | $0.04421 |
| Opus 5 | $0.02210 | $0.02210 |
| Sonnet 5 | $0.00884 | $0.00884 |
| Haiku 4.5 | $0.00442 | $0.00442 |
Grade A, and why
hybrid-harness-chaos-process-prm 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 11d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — hybrid-harness-chaos-process-prm (Pro Max)
Project Identity
Project: hybrid-harness-chaos-process-prm Version: 0.5.0 Domain: Platform Engineering — Continuous Delivery + Resilience Engineering + Security + Compliance + Adversarial Critique Audience: Fullstack developers, SREs, Platform Engineers, DevOps practitioners, Security engineers AI Compatibility: Claude Code (with plugin manifest), Codex, Gemini, GPT-4, and any instruction-following LLM agent
What This Project Does
This repository defines a 37-skill Agile workflow covering the complete SDLC from ideation to production operations, including adversarial critique:
| Domain | Purpose |
|---|---|
| Foundation | Orchestration, BA analysis, user flows, taste memory, progress tracking |
| CI/CD Engineering | Pipeline design, service onboarding, delegates, secrets, feature flags, templates, GitOps |
| Security | SAST, DAST, container scanning, dependency scanning, SBOM, supply chain security |
| Testing | CloakBrowser E2E, performance/load testing, visual regression |
| Chaos Engineering | Hypothesis-driven fault injection, blast radius control, steady state, game days |
| Verification | Continuous verification, observability, alerting, recommendations |
| Governance | OPA policies, cloud cost, release management, disaster recovery |
| Learning | Resilience scoring, postmortem RCA, compliance & audit |
| Research | Deep multi-source research, evidence synthesis, brainstorming debrief |
| Optimization | Latency, N+1, stress, atomicity, concurrency, security audit |
| Documentation | Technical specs, user flows, usage guides, README generation |
| Adversarial Critique | Devil's Advocate: stress-test decisions, detect fallacies, score arguments |
Quick Reference: Skill Index (37 Skills)
| # | Skill | Phase | Triggers |
|---|---|---|---|
| 00 | Orchestrator | Foundation | workflow, start, orchestrate |
| 01 | BA Requirements | Foundation | analyze, PRD, requirements, spec |
| 01-1 | User Flow Writing | Foundation | user flow, journey map, edge case, sad path |
| 02 | Taste Memory | Foundation | preference, always, never, I prefer |
| 03 | Progress Tracker | Foundation | status, progress, where are we |
| 04 | Pipeline Design | CI/CD | pipeline, CI/CD, stages, deploy |
| 05 | Service Onboarding | CI/CD | onboard, new service, register |
| 06 | Delegate Management | CI/CD | delegate, agent, install |
| 07 | Secrets Management | CI/CD | secret, credential, vault |
| 08 | Feature Flags | CI/CD | feature flag, FF, rollout, toggle |
| 09 | Template Library | CI/CD | template, reusable, stage template |
| 10 | GitOps | CI/CD | GitOps, ArgoCD, sync, drift |
| 11 | Security Scanning | Security | SAST, vulnerability, CVE, SBOM, scan |
| 12 | CloakBrowser Testing | Testing | test, E2E, browser, a11y, visual |
| 13 | Performance Testing | Testing | load test, stress, benchmark, k6 |
| 14 | Experiment Design | Chaos | chaos experiment, fault, inject |
| 15 | Hypothesis Validation | Chaos | hypothesis, steady state, SLO |
| 16 | Blast Radius Control | Chaos | blast radius, scope, limit, abort |
| 17 | Steady State | Chaos | steady state, baseline, probe |
| 18 | Infrastructure Faults | Chaos | node drain, disk, CPU, EC2 stop |
| 19 | Application Faults | Chaos | pod delete, container kill, latency |
| 20 | Game Day Planning | Game Day | game day, chaos day, war game |
| 21 | CV Verification | Verify | continuous verification, canary |
| 22 | Observability | Verify | observability, dashboard, metrics |
| 23 | Alerting | Verify | alert, notify, recommend, remediate |
| 24 | Policy Governance | Govern | OPA, policy, governance, compliance |
| 25 | Cloud Cost | Govern | cost, budget, optimization, CCM |
| 26 | Resilience Scoring | Govern | resilience score, maturity, report |
| 27 | Postmortem | Learn | postmortem, RCA, learning, action |
| 28 | Release Management | Govern | release, deploy prod, change mgmt |
| 29 | Disaster Recovery | Govern | DR, failover, RTO, RPO, backup |
| 30 | Compliance & Audit | Learn | compliance, audit, SOC2, HIPAA, GDPR |
| 31 | Strategic Creator | Any | think bigger, brainstorm, propose, innovate, upgrade |
| 32 | Deep Research | Any | research this, find papers, literature review, evidence for |
| 33 | System Optimization | Any | optimize, latency, N+1, stress test, CCU, atomicity, race condition, security audit |
| 34 | Documentation Writing | Any | docs, README, user guide, technical spec, userflow, usage instructions, how to use |
| 35 | Devil's Advocate | Any | challenge this, stress-test, devil's advocate, find flaws, counter-argument, red team, critique |
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.
- 11d ago First seen · 421 lines · 4,421 tokens per session scan A 0825aa419ab5
hybrid-harness-chaos-process-prm CLAUDE.md is an instructions file published in the GitHub repository dungnotnull/hybrid-harness-chaos-process-prm (19 stars, last pushed 3mo ago), licensed MIT. It adds 4,421 tokens to every session, about $0.0221 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 2026-08-30.
Other instructions, from other repositories
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.
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.
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.
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).
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.