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 dayfinggg/openai-codex-agent-skills --skill diagnosegit clone --depth 1 https://github.com/dayfinggg/openai-codex-agent-skillsWrote 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/dayfinggg/openai-codex-agent-skills/diagnose)<a href="https://agentmods.dev/skills/dayfinggg/openai-codex-agent-skills/diagnose"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/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/dayfinggg/openai-codex-agent-skills/diagnose"><img src="https://agentmods.dev/badge/skills/dayfinggg/openai-codex-agent-skills/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 | $0.00054 | $0.00516 |
| Opus 5 | $0.00027 | $0.00258 |
| Sonnet 5 | $0.00011 | $0.00103 |
| Haiku 4.5 | $0.00005 | $0.00052 |
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 5d 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose
Follow the governing instructions and the user's requirements for communication, code style, authorization, and delegation. This skill supplies task-specific guidance, not permission to expand the task. Its workflow and output fields describe internal checks and relevant content, not a mandatory response layout or a progress report. When used within broader authorized work, continue that work through completion rather than stopping to deliver this skill's intermediate result.
Replace speculation with a short feedback loop and a causal explanation.
Reproduce
Capture the exact symptom, environment, inputs, expected behavior, and observed behavior. Find the smallest reliable reproduction. If the failure is intermittent, identify the condition that changes its probability instead of adding arbitrary waits.
Preserve a working baseline or last-known-good observation before changing the experiment so later comparisons remain meaningful.
Narrow
Follow the failing value or event backward through boundaries. Compare a working and failing path when possible. Test one hypothesis at a time with the cheapest discriminating observation. Read logs and code around the first incorrect state, not only the final exception.
For ordering or concurrency failures, build a timestamped event trace with identities and state transitions, then reproduce the smallest relevant interleaving with coordination primitives rather than sleep-based timing.
Establish cause
A root cause must explain the symptom, the triggering conditions, and why the system did not prevent it. Verify the explanation by changing or isolating the causal condition without silently shipping a fix.
After establishing the cause, search the affected scope for analogous code, data, configuration, or tests that share the same faulty assumption. Report the likely family separately from the proven reproduction.
Boundaries
Do not implement a repair for a diagnosis-only request. Do not hide the symptom with retries, guards, or broader timeouts. Redact secrets and personal data from evidence.
What ships with it
1 file 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.
- 5d ago Changed · +2 lines a599b6efae05
- 7d ago Changed · +8 lines 04ec1003b6d5
- 12d ago First seen · 29 lines · 54 tokens per session scan A 24eaa61d1a79
diagnose is a skill published in the GitHub repository dayfinggg/openai-codex-agent-skills (4 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 516 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
bug-detective
This skill should be used when the user asks to "debug this", "fix this error", "investigate this bug", "troubleshoot this issue", "find the problem", "something is broken", "this isn't working", "why is this failing", or reports errors/exceptions/bugs. Provides systematic debugging workflow and common error patterns.
tldr
TLDR code analysis — call graphs, semantic search, impact, dataflow, for far fewer tokens than reading the files raw. Triggers "who calls X", "what affects X", "blast radius", before large file reads or refactors.
fix
Debug and fix bugs/errors/failures, including merge conflicts and failing PR CI checks. Triggers "fix", "broken", "not working", "bug", "error", "failing", "merge conflict", "fix CI", "checks failing", console errors, build/test failures, regression.
explore
Read-only codebase investigation via Explore agent; also handles upward-zoom for unfamiliar code regions. Triggers "how does X work", "where is X", "find X", "understand X", "navigate codebase", "zoom out", "bigger picture", "where does this fit".
refactor
Behavior-preserving restructuring of code NOT in your current diff — extract modules, rename across files, pay down tech debt. For just-changed code use /zero-tech-debt. Triggers "refactor X", "restructure", "extract Y from Z".
triage
First-pass review of a client or unfamiliar repo — sweep for glaring issues, report ranked findings. READ-ONLY on external repos. Triggers "triage this repo", "point out glaring issues", "first pass on this client repo".