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 Cody-W-Tucker/Cognitive-Assistant --skill verify-before-trustgit clone --depth 1 https://github.com/Cody-W-Tucker/Cognitive-AssistantWrote 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/cody-w-tucker/cognitive-assistant/verify-before-trust)<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/verify-before-trust"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/verify-before-trust/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/cody-w-tucker/cognitive-assistant/verify-before-trust"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/verify-before-trust.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 | $0.00029 | $0.00279 |
| Opus 5 | $0.00015 | $0.00139 |
| Sonnet 5 | $0.00006 | $0.00056 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
verify-before-trust 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 11d 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
When To Use
Load this after a claim, fix, rewrite, migration, generated artifact, or handoff needs proof before it is trusted. The skill owns post-claim and post-change verification.
Use it when the work is already asserted as done, correct, aligned, or improved, and the next responsible move is to test that assertion against evidence.
Do Not Use
Do not use this for initial inspection, root-cause diagnosis, mode selection, decision packaging, or action-forcing. It starts after there is something specific to verify.
What To Do
- Identify the claim being tested in one sentence.
- Choose the smallest verification that actually bears on that claim: test, lint, diff, rendered output, replayed workflow, checksum, manual check, or acceptance command.
- Report the result without laundering uncertainty. Passing a narrow check proves only the narrow claim.
- If verification is blocked, state the blocker and the next evidence needed.
- Do not substitute confidence, consistency, or intention for proof.
Output Shape
Return the claim, verification performed, result, and any remaining unverified surface.
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.
- 11d ago First seen · 26 lines · 29 tokens per session scan A cea36f57dcd9
verify-before-trust is a skill published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 24d ago), licensed Apache-2.0. It adds 29 tokens to every session and 279 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
debug
Systematic bug investigation with a five-phase framework: reproduce, narrow, diagnose, fix, verify. Supports automated regression bisect via --regression flag. Produces a structured debug report with root cause analysis, regression test, and CQ/Q self-evaluations.
refactor
Refactor existing code by extracting helpers, splitting files, removing duplication, or untangling dependencies. Supports resumable and batch runs. Use for structural changes that preserve behavior; use zuvo:build for new features.
tdd-cycle
Red-Green-Refactor TDD loop with mandatory false-positive check.
system-lifecycle
Orchestrate the full SDLC from Requirement to Code to Test (Traceability).
qa
Interactive /gobby qa launcher. Dispatches the shared qa-reviewer agent for a task.
development-discipline
Developer-agent discipline for test judgment, validation evidence, and TDD-required task escalation.