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 skills/changzhiai/claude-code-patch/verifynpx skills add changzhiai/claude-code-patch --skill verifygit clone --depth 1 https://github.com/changzhiai/claude-code-patchWhat 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 | $0.00013 | $0.00029 |
| Opus 5 | $0.00006 | $0.00015 |
| Sonnet 5 | $0.00003 | $0.00006 |
| Haiku 4.5 | $0.00001 | $0.00003 |
Grade A, and why
verify 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.
What it actually says
Run the verification process to ensure the code change is correct.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 6 lines · 13 tokens per session scan A f3fa7b5c896e
verify is a skill published in the GitHub repository changzhiai/claude-code-patch (11 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 29 once invoked, about $0.0001 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 skills, from other repositories
context-okf-llm-ingest
Use when extracting a codebase's implementation decisions into Metatron with an LLM/agent instead of metatron ingest — authoring candidate decisions as Open Knowledge Format (OKF) markdown files locally for review.
context-okf-promote-candidates
Use when promoting reviewed Metatron candidate decisions to canonical in a git/CI flow — moving Open Knowledge Format (OKF) files from candidate/ to decisions/. The agent performs only human-named moves; it never decides what to promote.
phoenix-intent
Decompose a high-level vague intent into N concrete /goal instances (≤5), each with its own phoenixsense acceptance check, proven complete via composite phoenixaccept (all N sawred AND greenafterred AND currentlygreen). Use when a task is multi-faceted (build + integrate + configure + notify) with independent or…
phoenix-mission
Run an N-goal DAG under the Phoenix supervisor — dependency-ordered execution with worktree isolation, lease fencing, budgets, a durable run ledger, and per-goal trace chains, on the local machine or dispatched to GitHub Copilot cloud agents. Use when goals have prerequisites, when a failure must contain its blast…
phoenix
The meta-skill that routes a task to the right Phoenix lifecycle skill and enforces the non-negotiable operating laws. Use at the start of any session or task to decide which Phoenix skill applies. Phoenix is a self-healing, token-efficient engineering harness — every stage verifies its work with an objective check…
phoenix-context
Assemble the cheapest sufficient context for a task — route structural questions (who calls X, what breaks if I change Y, what inherits from Z) to the prebuilt code graph instead of grepping and re-reading files, and pull the relevant subgraph/snippet rather than whole directories. Use on any non-trivial codebase…