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 n-n-code/n-n-code-skills --skill project-platform-diagnosegit clone --depth 1 https://github.com/n-n-code/n-n-code-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/n-n-code/n-n-code-skills/project-platform-diagnose)<a href="https://agentmods.dev/skills/n-n-code/n-n-code-skills/project-platform-diagnose"><img src="https://agentmods.dev/badge/skills/n-n-code/n-n-code-skills/project-platform-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/n-n-code/n-n-code-skills/project-platform-diagnose"><img src="https://agentmods.dev/badge/skills/n-n-code/n-n-code-skills/project-platform-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 | $0.00042 | $0.00558 |
| Opus 5.5 | $0.00017 | $0.00223 |
| Sonnet 5.5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
project-platform-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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Platform Diagnose
This overlay can stand alone for environment-only triage. Add matching language or discipline guidance when the diagnosis reaches source code or a specialized implementation boundary.
When to use
The problem differs by operating system, architecture, terminal, shell, CI, container, headless mode, installed runtime, service environment, or another platform fact.
Not for
Do not use this as primary for a reproducible logic bug (use the matching
principle skill and add project-core-dev only when repository-specific
completion evidence is not concrete), a known config-contract defect
(project-config-and-tests), Playwright harness or browser installation repair
(setup-playwright), vendored dependency ownership (project-vendor-boundary),
or release artifact layout (project-release-maintainer). Start here only while
the environment remains a plausible cause, then hand off when the failure is
isolated.
Diagnostic Workflow
- Inspect the failing command's side effects before rerunning it. Reproduce it within existing authority, using an isolated or check-only variant when needed, and capture exit status and relevant output. A failed install, migration, or deployment is not automatically safe to repeat. Separate build or install failures from startup and runtime failures.
- Record only relevant non-secret facts: OS, architecture, runtime and tool versions, shell or terminal mode, local versus CI or container, filesystem and permission assumptions, and required services. Never dump the full environment or expose credentials.
- Compare a working and failing environment when both exist. Build the smallest difference set and change one plausible variable at a time.
- Prefer built-in diagnostics and reproducible smoke checks. Use temporary directories, disposable containers, or other reversible probes when available; clean up created state.
- Classify direct observations separately from hypotheses. Distinguish an environment limitation, missing dependency, install defect, unsupported platform, config defect, and app regression before recommending a fix.
- Report whether the issue reproduced, the discriminating evidence, remaining unknowns, and the next smallest probe. Implement a code, config, setup, or release fix when the request includes repair, using the matching skill and existing authorization; otherwise report the diagnosis.
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 Changed · +4 lines 75c6d9727496
- 1mo ago First seen · 52 lines · 42 tokens per session scan A aa0b773a17b1
project-platform-diagnose is a skill published in the GitHub repository n-n-code/n-n-code-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 558 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
triage-issue
Verify an issue, persisted audit finding, or unresolved review finding against current code, classify it, and write only the contracted forge/ledger outcome. Supports independent batches and an immediate-fix review-finding route. Triggers: "triage-issue", "triage issue N", "triage this finding", "is this trigger met".
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
meter-reconcile
Skill-native CocoMeter transcript reconciliation and adapter canary. Replaces the former meter-reconcile and adapter-self-test runtime helpers.
stall
Show CocoStall loop and no-progress detection status.
stall-reset
Reset CocoStall counters after an operator-approved recovery.