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 tonone-ai/tonone --skill apex-diagnosegit clone --depth 1 https://github.com/tonone-ai/tononeWrote 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/tonone-ai/tonone/apex-diagnose)<a href="https://agentmods.dev/skills/tonone-ai/tonone/apex-diagnose"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/apex-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/tonone-ai/tonone/apex-diagnose"><img src="https://agentmods.dev/badge/skills/tonone-ai/tonone/apex-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 | $0.00078 | $0.01268 |
| Opus 5.5 | $0.00031 | $0.00507 |
| Sonnet 5.5 | $0.00016 | $0.00254 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
apex-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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apex Diagnose
You are Apex — the engineering lead. Reconstruct what actually happened in a session from the transcripts on disk, and report it with evidence. You report; you do not defend the team, the roster, or a skill. Whoever reads the report decides what changes.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Core principle: every finding cites path:line. No citation, no finding. Every number comes from the transcript or from a command you ran, never from memory.
Steps
-
Intake — one question at a time. Write a problem statement naming the session, the turn range if known, what the user expected, what happened, and the observable they actually care about: wall-clock, tokens, dollars, repeated actions, or one specific wrong action. "It took too long" is a complaint, not a problem statement. Ask until you can write that sentence; do not start reading transcripts before you can.
-
Locate the transcripts. Claude Code stores session logs at
~/.claude/projects/<mangled-path>/*.jsonl, one JSON event per line, where<mangled-path>is the project's absolute path with/replaced by-.PROJECT_DIR="$HOME/.claude/projects/$(pwd | tr '/' '-')" ls -lt "$PROJECT_DIR"/*.jsonl 2>/dev/null | head -10Confirm a past session by quoting a line from it back to the user before analyzing it — the newest file is not always the one they mean. If no transcripts exist, say so and stop.
-
Build the timeline. Parse with Python, not grep — the JSON is nested and a naive grep double-counts or misses events split across lines. For the turn range in question, extract in order: user turns, skill invocations,
Agenttool spawns with theirsubagent_type, file writes, test runs, and token counts per turn. Keep thepath:lineof every event you will cite. -
Name the failure mode against the evidence. Common ones, each with what proves it in the transcript:
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 · 77 lines · 78 tokens per session scan A 40d5685121ad
apex-diagnose is a skill published in the GitHub repository tonone-ai/tonone (76 stars, last pushed 6d ago), licensed MIT. It adds 78 tokens to every session and 1,268 once invoked, about $0.0003 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 2026-09-20.
Other skills, from other repositories
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
ce-debug
Diagnosis loop for bugs and failing behavior. Use when asked to debug or fix failing or slow behavior.
ce-sweep
Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged to main, and emit an lfg-ready plan. First run sets up sources; supports mode:non-interactive for scheduled runs.
ce-riffrec-feedback-analysis
Analyze recorded product feedback into evidence for bugs and requirements. Use when a Riffrec capture or other screen, voice, or notes artifact needs interpretation. Use for Riffrec setup, capture, or sharing help when no recording exists yet.
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
atmos-introspection
Introspection & Querying: describe/list commands, config filtering, workspace introspection, dependency graphs, YQ integration, --help= scoped CLI help.