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 afaraha8403/balakit --skill refreshing-app-verifygit clone --depth 1 https://github.com/afaraha8403/balakitWrote 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/afaraha8403/balakit/refreshing-app-verify)<a href="https://agentmods.dev/skills/afaraha8403/balakit/refreshing-app-verify"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/refreshing-app-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/afaraha8403/balakit/refreshing-app-verify"><img src="https://agentmods.dev/badge/skills/afaraha8403/balakit/refreshing-app-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 | $0.00072 | $0.00478 |
| Opus 5.5 | $0.00029 | $0.00191 |
| Sonnet 5.5 | $0.00014 | $0.00096 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
refreshing-app-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.
What it actually says
Refresh an app verify skill
Leading words: source then live, proven corrections, never product code.
Upkeep for a skill from generating-app-verify. The unit is the
feature, not every sentence.
Copy these steps into the todo list verbatim. Skip with skip: <reason>.
- Locate
skills/verify-*/(or the project's verify skill). None → stop and point at generating-app-verify. - Index hygiene on the feature-map README.
- Source wave: one read-only subagent per feature file. Children never drive or edit.
- Reconcile recipes. Flag user-facing surfaces missing from the map only with a source path.
- Live pass: exercise every feature at least once. Doctor before first drive and after failed drives. Evidence survives cleanup.
- Triage: map drift → fix the map. Harness gap → fix harness. App broken → report, do not paper over.
- Outcome: clean (no PR) / changed (one PR of proven corrections) / blocked (say what blocked).
Edit scope
Only the verification skill directory. A behavior the map describes that the app no longer does is doc drift (fix the map) or a product regression (report it).
Reply contract
Outcome, features covered, unreachable prerequisites, confirmed drift.
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 · 48 lines · 72 tokens per session scan A fe4a8856154a
refreshing-app-verify is a skill published in the GitHub repository afaraha8403/balakit (1 stars, last pushed 29d ago), licensed MIT. It adds 72 tokens to every session and 478 once invoked, about $0.0003 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 2026-09-11.
Other skills, from other repositories
working-effectively-with-legacy-code
Apply Michael Feathers-inspired legacy-code rules when changing hard-to-test code safely with characterization tests, seams, sprout methods, or wrap methods.
refactoring-guru
Apply Refactoring.Guru-inspired rules when diagnosing code smells, choosing refactoring techniques, and stopping cleanup before uncontrolled redesign.
refactoring
Apply Martin Fowler-inspired refactoring rules when improving existing code structure while preserving observable behavior.
rtl-p5s-integration-test
P5 Tier 4 integration tests: cross-module data flow, reset propagation, boundary handshakes. Triggers 'integration test', 'end-to-end system verification'.
rtl-p5s-integration-test-policy
Internal reference: rtl p5s integration test policy (agent-loaded; do not invoke).
dpf-verify-on-live-install
Use when asked to functionally verify that a DPF feature works on the live install by driving the happy path on the running portal.