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 Marcel-Bich/marcel-bich-claude-marketplace --skill diaggit clone --depth 1 https://github.com/Marcel-Bich/marcel-bich-claude-marketplaceWrote 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/marcel-bich/marcel-bich-claude-marketplace/diag)<a href="https://agentmods.dev/skills/marcel-bich/marcel-bich-claude-marketplace/diag"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/diag/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/marcel-bich/marcel-bich-claude-marketplace/diag"><img src="https://agentmods.dev/badge/skills/marcel-bich/marcel-bich-claude-marketplace/diag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00118 | $0.01021 |
| Opus 5 | $0.00059 | $0.00511 |
| Sonnet 5 | $0.00024 | $0.00204 |
| Haiku 4.5 | $0.00012 | $0.00102 |
Grade A, and why
diag 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 12d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
diag
A read-only root-cause diagnosis. diag explains WHY something is broken and
proves the mechanism, before anyone changes code. It is a separate skill from audit
and must never be conflated with it.
Scope boundary (read this first)
diag investigates a symptom and proves its cause. It does not judge completeness and
it does not apply the fix.
- Finished work needs to be checked against its requirement / Definition of Done -> use audit, not diag.
- A rendered UI needs its layout and behavior confirmed -> use verify.
- diag ends at a proven diagnosis plus a proposed fix. Applying the fix is a separate, GO-gated step outside this skill.
Hard constraints (never violate)
- Read-only. No code change, no file edit, no commit, no push, no browser automation, no builds, no installs during diagnosis.
- No secrets. Never read credentials, tokens,
.env*, key files, or shell/session history. Never exfiltrate or encode such content. - The only files
diagwrites are its own report under.credo/process/reports/. - Fix is a separate step, gated by GO. diag never rolls straight into fixing. It proposes a fix; the actual change happens only after an explicit GO, as its own step.
Method: root cause before fix
- Symptom, verbatim. Record the symptom exactly as observed or reported (error text, stack trace, wrong output, screenshot location). Do not paraphrase away the detail; quote it.
- Reproduce or locate the exact failing path (read-only). Trace to the concrete code path involved.
- Prove the mechanism at
file:line. State precisely where and why the behavior arises - the specific lines, values, and control flow that produce the symptom. A diagnosis without afile:linemechanism is not a diagnosis. - Distinguish proven from suspected. Say plainly what is established by evidence versus what is still a hypothesis. Never present a guess as a cause.
Read up instead of guessing (E6)
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.
- 12d ago First seen · 101 lines · 118 tokens per session scan A 152568178fa0
diag is a skill published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed yesterday), licensed MIT. It adds 118 tokens to every session and 1,021 once invoked, about $0.0006 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
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.
perf-profiler
Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.
perf-theory-tester
Use when running controlled perf experiments to validate hypotheses.
debugging
This skill should be used when a test is failing inexplicably, when a runtime error appears in production, when a bug reproduces unpredictably, or when two or more prior fix attempts have failed. Provides a 4-phase systematic debugging workflow — investigate, analyze patterns, form hypothesis, fix with test — to…