Borrowing it
Nothing to install: this file belongs to sernote/audit-prompt-caching. 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/sernote/audit-prompt-caching/main/AGENTS.mdgit clone --depth 1 https://github.com/sernote/audit-prompt-cachingWrote 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/sernote/audit-prompt-caching/agents-md)<a href="https://agentmods.dev/instructions/sernote/audit-prompt-caching/agents-md"><img src="https://agentmods.dev/badge/instructions/sernote/audit-prompt-caching/agents-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 5.1 | $0.00625 | $0.00625 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade B, and why
audit-prompt-caching AGENTS.md scanned grade B 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 today.
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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
find . -name __pycache__ -type d -prune -exec rm -rf {} + Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Purpose
This repository maintains the portable audit-prompt-caching Codex/agent skill. The skill audits LLM prompt and prefix caching behavior, provider cache telemetry, prompt-prefix stability, cache ROI, and self-hosted KV/cache routing issues.
Layout
audit-prompt-caching/SKILL.md: main skill instructions and trigger surface.audit-prompt-caching/references/: provider and scenario references loaded selectively by the skill.audit-prompt-caching/scripts/: dependency-free Python audit helpers.audit-prompt-caching/evals/: behavioral and trigger eval prompts.tests/test_prompt_cache_scripts.py: unittest coverage for bundled scripts and package checks.tests/test_routing_logs.py: normalized routing evidence and CLI coverage.docs/superpowers/plans/: implementation plans for multi-step changes.
Development Rules
- Keep scripts dependency-free and Python stdlib-only unless the user explicitly approves otherwise.
- Use
apply_patchfor manual edits. - Preserve provider-specific behavior in references; avoid broad rewrites unless the task asks for them.
- For multi-step work, create a plan in
docs/superpowers/plans/YYYY-MM-DD-<feature>.mdbefore implementation. - Use TDD for script behavior changes: add or update a failing test, verify RED, implement minimal code, verify GREEN.
- Do not claim completion without fresh verification output.
Verification Commands
Run all script tests, including normalized routing evidence:
python3 -m unittest discover -s tests -p 'test_*.py'
Validate the skill package:
python3 audit-prompt-caching/scripts/validate_skill_package.py audit-prompt-caching
python3 audit-prompt-caching/scripts/run_trigger_eval.py audit-prompt-caching
Check Python syntax:
python3 - <<'PY'
from pathlib import Path
for path in [*Path('audit-prompt-caching/scripts').glob('*.py'), *Path('tests').glob('*.py')]:
compile(path.read_text(), str(path), 'exec')
print(f'ok {path}')
PY
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.
- today Changed · +1 lines · +25 tokens per session d88f272b2db7
- 7d ago First seen · 75 lines · 600 tokens per session scan B 26b6d836f4a5
audit-prompt-caching AGENTS.md is an instructions file published in the GitHub repository sernote/audit-prompt-caching (113 stars, last pushed yesterday), licensed MIT. It adds 625 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). 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).
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.
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.