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 sergeyklay/.agents --skill verify-implgit clone --depth 1 https://github.com/sergeyklay/.agentsWrote 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/sergeyklay/.agents/verify-impl)<a href="https://agentmods.dev/skills/sergeyklay/.agents/verify-impl"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/verify-impl/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/sergeyklay/.agents/verify-impl"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/verify-impl.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 | $0.00157 | $0.02394 |
| Opus 5.5 | $0.00063 | $0.00958 |
| Sonnet 5.5 | $0.00031 | $0.00479 |
| Haiku 4.5 | $0.00016 | $0.00239 |
Grade A, and why
verify-impl 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 1mo 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-vs-Implementation Verification
You are conducting a forensic verification - a systematic, evidence-based comparison of implemented code against its authoritative technical specification. You answer one question: does the implementation faithfully realize every requirement, constraint, design decision, interface contract, algorithm, and invariant defined in the specification?
The specification is the product of deliberate architectural work. Every footnote, every constraint, every edge-case note exists because an architect determined it was necessary. A missed requirement is a latent defect; a diverged algorithm is a behavioral bug; a weakened invariant is a potential security boundary violation.
Input
The user provides a path to a specification file (markdown). Read the spec in its entirety before classifying anything. The spec is the authoritative source of truth: if the code does not meet it, that is a failure of the implementation, not of the spec.
Workflow
The verification proceeds in seven phases. Each phase has a documented gate that prevents a specific failure mode (false positives, recency bias, severity inflation, missed cross-cutting concerns). Do not skip, merge, or abbreviate any phase.
Copy this checklist into your response and mark items as you complete them:
- Phase 1 - Build project context
- Phase 2 - Extract every verifiable requirement
- Phase 3 - Discover the implementation surface
- Phase 4 - Verify each requirement
- Phase 5 - Cross-cutting verification
- Phase 6 - Self-verification
- Phase 7 - Verdict and remediation
Phase 1 - Build project context
Before verifying anything, understand the system the spec lives within.
Project documentation. Search and read:
- Context files:
AGENTS.md - Project docs:
README.md,CONTRIBUTING.md, plusdocs/ordoc/directories - especially design and ADR sets - Build manifests:
package.json,go.mod,Cargo.toml,pyproject.toml, etc. - to understand the tech stack - Runtime model:
.env.example,docker-compose.yml,compose.yml,Makefile
What ships with it
5 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.
- 1mo ago Changed · -1 lines 55556ea98dd4
- 1mo ago Changed · -6 tokens per session 5226632afdf3
- 1mo ago First seen · 167 lines · 163 tokens per session scan A e23cc7c37b35
verify-impl is a skill published in the GitHub repository sergeyklay/.agents (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 157 tokens to every session and 2,394 once invoked, about $0.0006 per session on Opus 5.5. 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
review
Review Elixir/Phoenix changes before committing — bugs, security, Ecto, LiveView, and Oban anti-patterns, via parallel specialist agents. Use when asked to review changes, a component, a diff, or a PR.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
challenge
Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.