Borrowing it
Nothing to install: this file belongs to fokkerone/superspecs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fokkerone/superspecs/main/.skills/verify/SKILL.mdgit clone --depth 1 https://github.com/fokkerone/superspecsWrote 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/fokkerone/superspecs/verify)<a href="https://agentmods.dev/skills/fokkerone/superspecs/verify"><img src="https://agentmods.dev/badge/skills/fokkerone/superspecs/verify/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/fokkerone/superspecs/verify"><img src="https://agentmods.dev/badge/skills/fokkerone/superspecs/verify.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 | $0.00000 | $0.02993 |
| Opus 5.5 | $0.00000 | $0.01197 |
| Sonnet 5.5 | $0.00000 | $0.00599 |
| Haiku 4.5 | $0.00000 | $0.00299 |
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 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: verify
You are doing the final verification before the feature can be shipped.
Execution is complete. This skill runs in two sequential stages:
- Stage 1 — Check Tests: confirm the implementation works
- Stage 2 — Wiki Import: distill the knowledge
Gate: If Stage 1 fails for any reason — failing tests, skipped tests, uncovered scenarios — stop. Do not proceed to Stage 2. Fix first.
Stage 1 — Check Tests
1. Run the full test suite
<test-runner>
Expected output: all tests passing, zero failing, zero skipped.
Report the result:
Test suite: <date>
Total: <N>
Passing: <N> ✅
Failing: <N> ❌
Skipped: <N> ⚠️
Pending: <N> ⚠️
If anything is failing, skipped, or pending: stop. Report. Do not proceed.
2. Verify spec scenario coverage
Read superspec/specs/<slug>/spec.md. For every scenario:
Search the test files for a test covering that scenario. Use the GIVEN/WHEN/THEN as search anchors.
## Spec Coverage Report
### Requirement: <Name>
#### Scenario: <Name>
Status: ✅ covered
Test: `<test-file>:<line>` — `<test name>`
#### Scenario: <Edge case name>
Status: ❌ NOT COVERED
Action required: Write a test for this scenario
[...]
## Summary
Scenarios total: <N>
Covered: <N> ✅
Missing: <N> ❌
If any scenario is uncovered: this is a Critical gap. Write the missing test before proceeding.
3. Run tests with coverage (if available)
If the project has a coverage tool:
<coverage-tool> <test-runner>
Note:
- Overall coverage %
- Coverage of files touched by this feature
- Any significant uncovered branches
Coverage is informational — it informs judgment, but 100% coverage is not required. Scenario coverage (step 2) is required.
4. Check for regressions
Compare with baseline if available. Specifically check:
- Areas of the codebase adjacent to what was changed
- Integration points (APIs called, events emitted, etc.)
If any tests that were passing before this spec's execution are now failing: that's a regression. It must be fixed before proceeding.
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 First seen · 438 lines · 0 tokens per session scan A 4f3fac6b5350
verify is a skill published in the GitHub repository fokkerone/superspecs (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,993 tokens. 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
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
project-knowledge
Verified, actionable gotchas for oh-my-posh. Read the matching topic file BEFORE changing shell integration scripts (pwsh, zsh, bash, fish, cmd/Clink, nu, elvish, xonsh), terminal or pty behavior, WSL or e2e shell tests, Go internals (cache, segments, streaming, serve daemon, template rendering, output sanitization)…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
impl-validator
Independently check whether an implementation matches its stated goal and return PASS/WARN/FAIL with actionable issues. Use for second-opinion validation of an implementation or generated output.
self-improve-with-tinyfish
Enables Hermes to create new reusable skills for itself by researching live web sources with TinyFish Search and Fetch, analyzing source coverage, writing SKILL.md files, and installing them into Hermes memory. Use when the user asks Hermes to learn, teach itself, upgrade itself, or save a reusable capability.
performing-fuzzing-with-aflplusplus
Perform coverage-guided fuzzing of compiled binaries using AFL++ (American Fuzzy Lop Plus Plus) to discover memory corruption, crashes, and security vulnerabilities. The tester instruments target binaries with afl-cc/afl-clang-fast, manages input corpora with afl-cmin and afl-tmin, runs parallel fuzzing campaigns with…