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 diagnose-before-patchinggit 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/diagnose-before-patching)<a href="https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/diagnose-before-patching"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/diagnose-before-patching/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/diagnose-before-patching"><img src="https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/diagnose-before-patching.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 | $0.00298 |
| Opus 5 | $0.00015 | $0.00149 |
| Sonnet 5 | $0.00006 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
diagnose-before-patching 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 10d 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 only when something is broken, failing, regressing, contradictory, or behaving differently from the stated expectation. The skill owns cause-finding before repair.
Use it for build failures, runtime errors, test regressions, bad outputs, broken prompts, unreliable workflows, or operational symptoms where a patch would otherwise be a guess.
Do Not Use
Do not use this for ordinary pre-solution inspection, stylistic refinement, packaging a decision, simplifying a design, or proving a completed fix. If there is no failure state or symptom, this skill is too heavy.
What To Do
- State the observed failure and the expected behavior in concrete terms.
- Reproduce or localize the symptom before changing anything when feasible.
- Trace from symptom to likely cause using the smallest useful evidence: logs, tests, diffs, inputs, config, or runtime behavior.
- Change only what the cause explains. Avoid broad rewrites that merely pass near the symptom.
- If the cause remains uncertain, label the patch as provisional and keep the next check narrow.
Output Shape
Return the failure, evidence, likely cause, minimal patch, and the targeted check that would prove the cause was addressed.
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.
- 10d ago First seen · 26 lines · 29 tokens per session scan A 25b61d53da23
diagnose-before-patching is a skill published in the GitHub repository Cody-W-Tucker/Cognitive-Assistant (11 stars, last pushed 23d ago), licensed Apache-2.0. It adds 29 tokens to every session and 298 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
gateway-doctor
Use when diagnose and fix MCP gateway routing issues, health checks, and server connectivity problems. Use when working with gateway doctor.
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.
empirical-methods
Apply empirical and measurement methods to engineering decisions with sound experiment design, honest statistical interpretation, and root-cause analysis.
self-heal
Autonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation.
debug-discipline
Use when encountering any bug, test failure, or unexpected behaviour. Root cause investigation is mandatory before any fix attempt.
test-first
Use when implementing any feature, bug fix, or behaviour change - before writing implementation code. Enforces test-before-code discipline.