diagnose-before-patching

diagnose-before-patching is a skill for Claude Code, Codex from Cody-W-Tucker/Cognitive-Assistant. It costs 29 tokens per session (298 once invoked), scanned A, original, Apache-2.0.

A diagnosis-only workflow for broken software and unexpected results. It requires finding evidence for the cause before proposing a repair.

In plain words
What is it for?
Investigating build failures, runtime errors, test regressions, contradictory behavior, bad outputs, and unreliable workflows.
Why use it?
It reduces the risk of applying a patch that hides the symptom while leaving the real problem in place.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions OpenCode.

Good fit Investigating build failures, runtime errors, test regressions, contradictory behavior, bad outputs, and unreliable workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cody-w-tucker/cognitive-assistant/diagnose-before-patching
Install

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.

Any agent
npx skills add Cody-W-Tucker/Cognitive-Assistant --skill diagnose-before-patching
Clone the repo
git clone --depth 1 https://github.com/Cody-W-Tucker/Cognitive-Assistant

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for diagnose-before-patching

README.md
[![agentmods](https://agentmods.dev/badge/skills/cody-w-tucker/cognitive-assistant/diagnose-before-patching/github.svg)](https://agentmods.dev/skills/cody-w-tucker/cognitive-assistant/diagnose-before-patching)
Your own site
<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.

agentmods 80×15 button for diagnose-before-patching

Your own site · 80×15
<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>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 25b61d53da23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

workspaces/skills/core/diagnose-before-patching/SKILL.md · 26 lines

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.

Changes

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.

  1. 10d ago First seen · 26 lines · 29 tokens per session scan A 25b61d53da23

Subscribe to this mod's changes

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.