Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hmj1026/dhpknpx agentmods add skills/hmj1026/dhpk/change-verdictWrote 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/skills/hmj1026/dhpk/change-verdict)<a href="https://agentmods.dev/skills/hmj1026/dhpk/change-verdict"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/change-verdict/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/skills/hmj1026/dhpk/change-verdict"><img src="https://agentmods.dev/badge/skills/hmj1026/dhpk/change-verdict.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 | $0.00074 | $0.01780 |
| Opus 5 | $0.00037 | $0.00890 |
| Sonnet 5 | $0.00015 | $0.00356 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
change-verdict 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Verdict
Use the smallest mode that answers the question. This is a read-only observer of source, diffs, tests, documents, metadata, and tool output; it returns a verdict and text-only recommendations, never repository or review-state edits.
Modes
| Mode | Question answered | Read when |
|---|---|---|
code |
Is a fixed-point diff correct, safe, and consistent with its spec? | Reviewing code changes or a branch. |
pr |
Is a proposed PR complete and hygienic for its declared merge method? | Self-reviewing a branch or inspecting PR metadata. |
security |
Are security-sensitive paths exposed to OWASP risks or unsafe dependencies? | Auditing auth, input, secrets, dependencies, or security-sensitive changes. |
tests |
Do existing tests and acceptance evidence cover the behavior? | Reviewing test adequacy or tracing ACs to evidence. |
docs |
Is a document accurate, complete, and consistent with the code? | Reviewing Markdown, specs, READMEs, or design documents. |
risk |
What breaking surface, blast radius, and change-scope signals are present? | Assessing an uncommitted diff or large refactor. |
If --mode is omitted, infer one mode only when unambiguous; otherwise report
INCONCLUSIVE with the minimum clarification needed. Do not run multiple modes.
When NOT to Use
- Implement or fix a finding → use
flow-drive. - Trace an unfamiliar code path → use
code-trace. - Author or audit a skill → use
skill-forgeorskill-scope.
Shared read-only protocol
- Resolve a fixed point before reading findings: use a non-empty
git merge-base <base> HEADfor branch work, orHEADfor an uncommitted diff. Record the exact value. - Read the actual diff and relevant files yourself. Treat caller-provided summaries as navigation hints, never as evidence.
- Use file-and-line evidence for every material finding. Redact secrets, tokens, cookies, private keys, and personal data from output.
- Keep primary-model evidence separate from an optional CLI second opinion.
The primary path is complete without the CLI; unavailable or unrequested
CLI evidence is explicitly
degraded: primary model only. - Return a verdict without changing repository state. A missing fixed point,
unavailable dependency, unreadable scope, or contradictory evidence keeps
the result
INCONCLUSIVEorBLOCKED; it never becomes an assumed pass.
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 · 151 lines · 74 tokens per session scan A 3ed5db10d281
change-verdict is a skill published in the GitHub repository hmj1026/dhpk (2 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,780 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
plumb-line-audit
Use when auditing a diff or repository against the plumb-line principles — finds laundered uncertainty, boundary leaks, hardcoded priors, overstated maturity, outputs lacking recorded lineage, and baseline drift with no explanation. Read-only: it reports, never auto-fixes.
evaluator-review-contract
Internal Auto-Harness evaluator skill for sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.
second-pass-review
Independent audit of sanitized specs in workspace/output/. Three parallel LLM-based reviewer roles check structural leakage, content contamination, and behavioral completeness. Run AFTER Layer 5 sanitization, BEFORE implementation handoff.
check-pr
Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability, and returns PASS or FAIL with per-gate findings. Never invokes the merge button. Use when verifying a PR is ready to merge, polling lifecycle progress, checking mergeability, or babysitting a GitHub PR…
codex-review
Get an independent code review from OpenAI Codex (GPT-5) on uncommitted changes, a branch diff, a PR, or a specific module — returns findings grouped by severity with file:line references. Use when the user says "review this", "review my changes", "check this PR", "what did I miss", or before they commit or merge…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…