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/dyzcode/works-plugins/verify-public-commitnpx skills add DYZCODE/works-plugins --skill verify-public-commitgit clone --depth 1 https://github.com/DYZCODE/works-pluginsWhat 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 | $0.00060 | $0.00513 |
| Opus 5 | $0.00030 | $0.00257 |
| Sonnet 5 | $0.00012 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
verify-public-commit 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 yesterday.
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
Verify Public Commit
Use works_verify_public_repository only when all of these are known:
- the repository is public and hosted at
https://github.com/<owner>/<repo>; - the exact work being judged is represented by a lowercase 40-character commit SHA;
- a supported WORKS contract matches the claim.
Before calling either WORKS tool, confirm all three eligibility conditions locally from the request. If any condition is absent or the requested claim is runtime, build, test, deployment, or broad production readiness, abstain without calling a WORKS tool. Do not use contract lint to decide basic eligibility.
After eligibility is established, call works_verify_public_repository
directly. Use node-package only for package structure, lockfile, and declared
automation. Use env-safety only for its exact environment-template contract.
Call works_public_contract_lint only when the user explicitly asks to inspect
contract metadata without verifying a repository.
Never substitute a branch, tag, pull request number, abbreviated SHA, mutable archive URL, private repository, or local working tree. Never create or push a commit merely to satisfy this skill.
The verification result includes a deterministic report. Return that report
verbatim and stop. Do not paraphrase it, add a heading, or manually reconstruct
the receipt. The first line labels the exact receipt status:
passed: every declared static outcome passed.failed: at least one declared outcome was disproved.blocked: WORKS could not collect complete evidence.error: the verifier failed.
Before returning the report, require trust.pinned_key_identity to be
matched and trust.key_id to equal
sha256:ccdae125f1c40606597f0111b484689b. A mismatch is a hard failure. This is
a pinned key-identity check, not independent signature validation.
The complete signed receipt remains in the tool's structured receipt field.
Do not inspect unrelated local files, reread the bundled key, rehash it with a
different convention, or call additional tools merely to restate the result.
What ships with it
1 file 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.
- yesterday First seen · 47 lines · 60 tokens per session scan A bd10c1b71843
verify-public-commit is a skill published in the GitHub repository DYZCODE/works-plugins (0 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 513 once invoked, about $0.0003 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 skills, from other repositories
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…