Borrowing it
Nothing to install: this file belongs to VonTerraProject501c3/slushpile. 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/VonTerraProject501c3/slushpile/main/CLAUDE.mdgit clone --depth 1 https://github.com/VonTerraProject501c3/slushpileWrote 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/vonterraproject501c3/slushpile/claude-md)<a href="https://agentmods.dev/instructions/vonterraproject501c3/slushpile/claude-md"><img src="https://agentmods.dev/badge/instructions/vonterraproject501c3/slushpile/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/vonterraproject501c3/slushpile/claude-md"><img src="https://agentmods.dev/badge/instructions/vonterraproject501c3/slushpile/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 | $0.06799 | $0.06799 |
| Opus 5 | $0.03400 | $0.03400 |
| Sonnet 5 | $0.01360 | $0.01360 |
| Haiku 4.5 | $0.00680 | $0.00680 |
Grade A, and why
slushpile 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 10d 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.
This is a copy
100% identical to slushpile AGENTS.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
This repository ships one job-application pipeline to several coding agents. Ten skills and eight agent definitions are the product. Everything else is a manifest, a template, or a check.
Generated files
AGENTS.md is generated from CLAUDE.md. Never edit a generated file, and
never edit inside a BEGIN GENERATED / END GENERATED marker pair. The next
generator run deletes it.
| Generated | Built from |
|---|---|
all of AGENTS.md |
CLAUDE.md |
all of .cursor/skills/slushpile/SKILL.md |
skills/, agents/, the dispatch table |
all of .cursor/rules/slushpile.mdc |
the same |
the skills and agents regions of GEMINI.md |
skills/, agents/, the dispatch table |
the pipeline and reviewers regions of README.md |
skills/, the dispatch table |
the harness-snippet region of INSTALL.md |
skills/, agents/ |
the agent-table region of docs/architecture/agents-and-models.md |
agents/, the dispatch table |
all of docs/architecture/AGENTS.md |
docs/architecture/CLAUDE.md |
all of docs/diagrams/AGENTS.md |
docs/diagrams/CLAUDE.md |
the language-nav region of every translated page and its English original |
TRANSLATED and LANGUAGES |
the market-note region of every translated README.md |
MARKET_NOTE |
| the generated regions of every translated page | copied from the English page |
The dispatch table is in skills/adversarial-review/SKILL.md. It is the source
for the review's shape everywhere it appears.
Run this after editing CLAUDE.md, after adding, renaming, or removing a skill
or an agent, and after any change to the dispatch table:
python3 scripts/sync_docs.py
scripts/sync_docs.py --check is the CI gate.
Declare it or the gate fails
Every derived fact is looked up by name, and a name matching nothing is an error rather than a silent omission.
| When you | Also edit |
|---|---|
| add, rename, or remove a skill | SKILLS in scripts/sync_docs.py |
| reword a sentence stating a derived count | COUNT_CLAIMS |
| write a sentence counting a subset on purpose | COUNT_EXEMPT, with its reason |
write a hand-written file that lists every skill as /slushpile:<name> |
COMMAND_ROSTERS |
add a field to templates/preferences.yaml |
a skill or agent that reads it, or PREFERENCES_UNREAD with its reason |
| add a language to the mirror | CARDS in scripts/make_card.py |
| add a font weight to a template | FACES in scripts/install_fonts.py, and NOTICE.md |
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.
- 10d ago First seen · 546 lines · 6,799 tokens per session scan A ee61b40cbeef
slushpile CLAUDE.md is an instructions file published in the GitHub repository VonTerraProject501c3/slushpile (15 stars, last pushed 23d ago), licensed MIT. It adds 6,799 tokens to every session, about $0.0340 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to slushpile AGENTS.md, differing in 2 lines, and is treated as a copy.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.