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/ankitkr3/compounded/claude-mdgit clone --depth 1 https://github.com/ankitkr3/compoundedWhat 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 | $0.01314 | $0.01314 |
| Opus 5 | $0.00657 | $0.00657 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
compounded 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 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md (compounded repository)
This file is read by Claude Code when working inside this repo. It describes the codebase, conventions, and what to do (and not do) when proposing changes.
What this repo is
compounded is a Claude Code plugin that adds a trust gradient and verified skills on top of Claude's native memory primitives. The plugin layout follows the Claude Code plugin spec:
.claude-plugin/plugin.json— manifestskills/<name>/SKILL.md— built-in skills (5 of them)commands/<name>.md— slash commands (9 of them)agents/<name>.md— subagent definitions (1)hooks/hooks.json— lifecycle hooks (SessionStart, Stop, SessionEnd)scripts/*.py— Python implementation (no runtime deps; stdlib only)tests/— unittest suite
Conventions
- Python is stdlib-only. No third-party imports. compounded must not pull in dependencies for its core path. We pay this cost gladly to keep install friction at zero.
- Hooks must never fail loudly. A SessionStart or Stop hook that crashes the user's session is a P0 bug. Wrap in try/except and emit
{"continue": true, "suppressOutput": true}on any unexpected failure. See the bottom ofscripts/memory_inject.pyfor the pattern. - All paths go through
_lib.py. Don't hardcode paths in individual scripts. Add them to_lib.pyso they respectCOMPOUNDED_HOME. - All trust state changes log an event. Every promotion, demotion, verification, rejection, and use must call
log_event(). The event log is how the user audits the system. - No LLM calls from scripts. The scripts are deterministic Python. The only LLM call is the verifier subagent, which is dispatched through Claude Code's native agent system (not a direct API call).
How the lifecycle works
-
SessionStart hook (
memory_inject.py) — reads USER.md, injects it asadditionalContext. Runs in <100ms typically. -
During the session — the agent may invoke
skill_propose.py(via Bash) when it wants to save a procedure. The script validates frontmatter, runs a security scan, writes to.proposed/<name>/, and records to the trust DB.
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 · 102 lines · 1,314 tokens per session scan A d031f0b71adf
compounded CLAUDE.md is an instructions file published in the GitHub repository ankitkr3/compounded (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,314 tokens to every session, about $0.0066 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
ai CLAUDE.md
Instructions for formio/ai, covering claude.md, project overview, repository info, skills library and iterating on skills.
autovault CLAUDE.md
Instructions for autoworks-ai/autovault, covering claude.md, project, common commands, architecture and request flow.
magi-workflow CLAUDE.md
Instructions for howar31/magi-workflow, covering what this is, slash commands, subagents, project state model and project document tiers.
codegraph AGENTS.md
Instructions for lzehrung/codegraph, covering agent directives, general and path, cache, and review safety.
superpowers-graph CLAUDE.md
Claude Code instructions for RonMizrahi/superpowers-graph, covering superpowers-graph — repository guide, sources of truth, changing the graph — the eval ships with the change and rules that are not obvious from the code.
ai-software-architect AGENTS.md
AGENTS.md instructions for codenamev/ai-software-architect, covering agents.md - ai software architect framework, project overview, framework development setup, repository structure and installation for framework development.