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 skills add hiendinhngoc/unknowns --skill verify-refgit clone --depth 1 https://github.com/hiendinhngoc/unknownsWrote 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/hiendinhngoc/unknowns/verify-ref)<a href="https://agentmods.dev/skills/hiendinhngoc/unknowns/verify-ref"><img src="https://agentmods.dev/badge/skills/hiendinhngoc/unknowns/verify-ref.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 5.1 | $0.00060 | $0.00675 |
| Opus 5 | $0.00030 | $0.00338 |
| Sonnet 5 | $0.00012 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
verify-ref 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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reference Verification
Prove you understand the reference implementation BEFORE porting it. Misunderstood references produce confidently wrong ports.
Write no implementation code until the user confirms the comprehension proof below.
Process
-
Locate the reference. Use the argument or conversation context. If ambiguous, ask which implementation is the reference — don't guess.
-
Set a behavioral boundary, then read it fully. Read the referenced unit, its direct callers, and direct dependencies that affect observable behavior. Follow deeper calls only while they change outputs, side effects, errors, or ordering. List unresolved or external dependencies instead of recursively expanding without a stop condition.
-
Produce the comprehension proof, covering:
- Data flow: inputs → transformations → outputs, in order
- Edge cases handled: every guard, fallback, retry, and special case, and what each protects against
- Invariants: what must remain true before/after (ordering, uniqueness, idempotency, transactional boundaries)
- Hidden dependencies: globals, config, environment, call-order assumptions, side effects the signature doesn't show. For UI code, also name the framework semantics the reference leans on: lifecycle hooks that fire once vs. per-render, view identity, and task/cleanup-on-teardown behavior — these are where ports break silently.
Proportionality: for a small same-repo adaptation (roughly ≤30 lines, no concurrency, no money/auth/persistence), a short proof of just Data flow and What would break if I got this wrong? suffices — but step 2's full read of the reference and its callers is never skipped; that read is where latent bugs surface.
-
Self-challenge. Add a section: "What would break if I got this wrong?" — name the 2-3 misreadings most likely to cause a subtly wrong port and say why your reading is correct (cite file:line evidence).
-
Gate. Ask the user to confirm the proof or correct it. Only after confirmation may implementation begin. A plan the user already approved that names this exact port also counts as confirmation — say the proof is being accepted under that approval and proceed. Otherwise, if no interactive user is available, stop after the proof and identify the exact uncertainty that needs review; do not silently treat the proof as approval.
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.
- 8d ago First seen · 63 lines · 60 tokens per session scan A d4ccf593f91c
verify-ref is a skill published in the GitHub repository hiendinhngoc/unknowns (9 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 675 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
ck-signatures
Extract all method/property signatures from C#, TypeScript, Kotlin, and Python files using live AST parsing. Use after ck find-files has identified the relevant folder, when evaluating multiple candidate files to avoid reading full file content.
plannotator
Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and exporting or sharing Guided Reviews. Invoke when asked to use Plannotator for anything not covered by a more specific…
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
agtx-review
Self-review completed work. Check for correctness, edge cases, and code quality. Write review to .agtx/review.md and stop.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…