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/agenticvault/agentic-vault/claude-mdgit clone --depth 1 https://github.com/agenticvault/agentic-vaultWrote 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/agenticvault/agentic-vault/claude-md)<a href="https://agentmods.dev/instructions/agenticvault/agentic-vault/claude-md"><img src="https://agentmods.dev/badge/instructions/agenticvault/agentic-vault/claude-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 | $0.01489 | $0.01489 |
| Opus 5 | $0.00745 | $0.00745 |
| Sonnet 5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
agentic-vault 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 4d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentic-vault
Required Checks (Stop Hook enforced)
| Change Type | Must Run | Can Skip |
|---|---|---|
.ts/.js code |
/codex-review-fast -> /precommit |
- |
.md docs |
/codex-review-doc |
/codex-review-fast |
| Comments only | - | All |
Before PR: /pr-review
Workflow
Feature: develop -> write tests -> /verify -> /codex-review-fast + /codex-test-review -> /precommit -> /pr-review
Bug fix: /issue-analyze -> /bug-fix -> investigate -> fix -> regression test -> /verify -> /codex-review-fast -> /precommit
Auto-Loop Rule ⚠️
After editing code or docs, you MUST run the review command in the same reply — do not stop, do not ask, do not just summarize.
| After editing... | Immediately run | Then on pass |
|---|---|---|
.ts/.js/.jsx/.tsx code |
/codex-review-fast |
/precommit |
.md docs |
/codex-review-doc |
(done) |
| Review found issues | Fix all → re-run same review | — |
Declaring ≠ Executing: Saying "should run review" without invoking the Skill tool is a violation. Summary ≠ Completion: Outputting a table then stopping is a violation.
Full spec: @rules/auto-loop.md
Test Requirements
| Change Type | Required Tests | File Mapping |
|---|---|---|
| New Service/Provider | test/unit/ required |
src/core/xxx.ts -> test/unit/core/xxx.test.ts |
| Modify existing logic | Existing pass + new logic | src/providers/*.ts -> test/unit/providers/*.test.ts |
| Bug fix | Regression test | - |
| New MCP tool | Unit test | src/agentic/mcp/tools/xxx.ts -> test/unit/agentic/mcp/tools/xxx.test.ts |
Coverage: happy path + error handling + edge cases (null, empty, extremes)
Command Quick Reference
| Command | Description | When |
|---|---|---|
/codex-brainstorm |
Adversarial brainstorm | Exploration |
/feasibility-study |
Feasibility analysis | Requirements |
/tech-spec |
Generate tech spec | Design |
/review-spec |
Review tech spec | Design |
/deep-analyze |
Deep analysis + roadmap | Design |
/project-brief |
PM/CTO executive summary | Design |
/codex-architect |
Architecture advice | Design |
/codex-implement |
Codex writes code | Development |
/bug-fix |
Bug fix workflow | Bug fixing |
/feature-dev |
Feature development | Development |
/code-explore |
Code exploration | Understanding |
/git-investigate |
Track code history | Finding source |
/issue-analyze |
Issue deep analysis | Root cause |
/repo-intake |
One-time project scan | Onboarding |
/verify |
Run tests | Development |
/codex-review-fast |
Quick review (diff) | Required |
/codex-review |
Full review (lint+build) | Important PR |
/codex-review-branch |
Full branch review | Important PR |
/codex-cli-review |
CLI review (full disk) | Deep review |
/codex-review-doc |
Review .md files | Doc changes |
/codex-explain |
Explain complex code | Understanding |
/precommit |
lint + typecheck + test | Required |
/precommit-fast |
lint + test (no build) | Quick check |
/codex-security |
OWASP Top 10 | Security-sensitive |
/codex-test-gen |
Generate unit tests | Adding tests |
/codex-test-review |
Review test coverage | Required |
/post-dev-test |
Post-dev test completion | After feature |
/check-coverage |
Test coverage analysis | Quality |
/dep-audit |
Dependency vulnerability audit | Periodic / PR |
/update-docs |
Sync docs with code | Doc changes |
/doc-refactor |
Simplify documents | Doc changes |
/create-request |
Create/update request docs | Planning |
/create-skill |
Create new skills | Tooling |
/simplify |
Code simplification | Refactoring |
/de-ai-flavor |
Remove AI artifacts | Doc changes |
/zh-tw |
Rewrite in Traditional Chinese | i18n |
/install-rules |
Install plugin rules to .claude/rules/ | Onboarding |
/install-hooks |
Install plugin hooks to .claude/ | Onboarding |
/project-setup |
Auto-detect and configure project | Onboarding |
/pr-review |
PR self-review checklist | Before PR |
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.
- 4d ago First seen · 133 lines · 1,489 tokens per session scan A fba23f8e6747
agentic-vault CLAUDE.md is an instructions file published in the GitHub repository agenticvault/agentic-vault (4 stars, last pushed 6mo ago), licensed MIT. It adds 1,489 tokens to every session, about $0.0074 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
prb-math AGENTS.md
Instructions for PaulRBerg/prb-math, covering prbmath, stack, structure, commands and development.
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
solidity-language-server AGENTS.md
Instructions for asyncswap/solidity-language-server, covering agents, prerequisites: ast identity model, the two id types, the src string format and why file ids are unstable from solc.
suwappubot CLAUDE.md
Claude Code instructions for 0xSoftBoi/suwappubot, covering claude.md, workflow, response length, git conventions and git operations.
suwappubot AGENTS.md
AGENTS.md instructions for 0xSoftBoi/suwappubot, covering agents.md — executable agent policy, ground rules, repo skills (reuse before building), where things live and knowledge base.
nft-mint-agent AGENTS.md
Instructions for dhasap/nft-mint-agent, covering agents.md, your job, pick the path (decision tree), how to call the tools and hard rules.