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 SetraTheXX/Codex-Engineering-Workflow-Pack --skill diagnosegit clone --depth 1 https://github.com/SetraTheXX/Codex-Engineering-Workflow-PackWrote 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/setrathexx/codex-engineering-workflow-pack/diagnose)<a href="https://agentmods.dev/skills/setrathexx/codex-engineering-workflow-pack/diagnose"><img src="https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/diagnose/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/setrathexx/codex-engineering-workflow-pack/diagnose"><img src="https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/diagnose.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 | $0.00048 | $0.01135 |
| Opus 5.5 | $0.00019 | $0.00454 |
| Sonnet 5.5 | $0.00010 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
diagnose 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose
Diagnose bugs by building a reliable feedback loop, proving the symptom, narrowing the cause, fixing the smallest responsible behavior, and leaving a regression check behind.
Do not jump straight to a fix. A plausible fix without a reproduced symptom is guesswork.
Read First
Before changing code, inspect project setup:
docs/agents/test-commands.mddocs/agents/domain.mdCONTEXT.md- relevant ADRs under
docs/adr/ - package scripts or equivalent task definitions
If setup docs are missing, infer commands from the repo. If commands remain unclear, ask the user one focused question.
Use the repo's domain language when describing the failure and suspected modules.
Workflow
1. State The Symptom
Restate the user-visible failure in one or two sentences.
Capture:
- What is expected.
- What actually happens.
- Where it happens.
- Whether it is deterministic, flaky, or performance-related.
If the symptom is ambiguous, ask for the missing observation before changing code.
2. Build A Pass/Fail Feedback Loop
Create or identify the fastest command or action that can prove the bug exists.
Prefer this order:
- Focused failing test.
- Existing test command that already fails for the right reason.
- CLI command with fixture input.
- HTTP request against local dev server.
- Browser automation for UI bugs.
- Small throwaway harness near the relevant code.
- Replayed payload, log, trace, or fixture.
- Repeated stress loop for flaky behavior.
The loop must be:
- Runnable by Codex.
- Specific to the user's symptom.
- Deterministic when possible.
- Fast enough to repeat.
If no loop can be built, stop and explain what was tried. Ask for a log, fixture, repro steps, recording, environment access, or permission to add temporary instrumentation.
See references/feedback-loop-patterns.md for options.
3. Reproduce
Run the loop and verify it fails for the same reason the user reported.
Record:
- Command or action used.
- Exact failure text, wrong output, timing, or visible behavior.
- Whether the failure repeated.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 200 lines · 48 tokens per session scan A 32174628352d
diagnose is a skill published in the GitHub repository SetraTheXX/Codex-Engineering-Workflow-Pack (1 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 1,135 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
pdlc-lint
A code-quality checker that runs static analysis, style checks, type checks, and other project-configured tools. It supports checking, safely fixing eligible problems, and setting up a lint toolchain.
pdlc-perf
A workflow for finding and improving performance problems in a specified backend service or frontend application. It examines areas such as database queries, caching, response times, loading, rendering, and network use, then records its findings in a report.
debugging
Systematic root-cause investigation for hard bugs.
icode
A Chinese-language, end-to-end coding workflow with separate steps for planning, review, approval, implementation, checking, and final audit. It also includes optional requirement drafting and log-based cause analysis.
pdlc-fix
An automated bug-fixing workflow that locates a reported bug, reproduces it with a test, applies a minimal fix, runs tests, and updates the relevant documentation.
adobe-illustrator-scripting
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system…