Borrowing it
Nothing to install: this file belongs to radiantlogicinc/fastworkflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/radiantlogicinc/fastworkflow/main/.claude/skills/fastworkflow-diagnostics-and-tooling/SKILL.mdgit clone --depth 1 https://github.com/radiantlogicinc/fastworkflowWrote 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/radiantlogicinc/fastworkflow/fastworkflow-diagnostics-and-tooling)<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-diagnostics-and-tooling"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-diagnostics-and-tooling.svg" alt="Measured on agentmods" 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 | $0.00202 | $0.04995 |
| Opus 5 | $0.00101 | $0.02498 |
| Sonnet 5 | $0.00040 | $0.00999 |
| Haiku 4.5 | $0.00020 | $0.00500 |
Grade A, and why
fastworkflow-diagnostics-and-tooling 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 8d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fastWorkflow diagnostics and tooling — measure, don't eyeball
Runbook for observing what a fastWorkflow workflow actually did and what state
its artifacts are actually in. Ships four tested, read-only scripts in
scripts/ plus a map of every observability surface the framework already
has. All paths are repo-relative to the fastWorkflow repo root; all facts
verified against v2.22.2 (commit c33b9a5).
When to use / when NOT to use
Use this skill when you need to:
- dump/inventory a workflow's
___command_info/(commands, utterance counts, thresholds, model files, DSPy few-shot artifacts) - decide "rebuild vs stale vs fine" for
command_directory.json/routing_definition.json(the v2.22.1 fingerprint) - capture or read a turn's command trace: live CLI traces, the per-workflow
observability.sqlite3(turns + spans + artifacts), the server response'stracesfield,TurnOutput - get numbers on a trained intent classifier (per-command accuracy on seeds, confusion pairs, ambiguity/fallback rates)
- control logging verbosity, inspect the DSPy cache, or use the K8s probes
Do NOT use this skill for — go to the sibling instead:
| Need | Sibling skill |
|---|---|
| symptom → root-cause triage of a failure | fastworkflow-debugging-playbook |
| how the BERT two-tier/threshold/DSPy pipeline works | fastworkflow-nlu-pipeline-reference |
| env var / CLI flag catalog and defaults | fastworkflow-config-and-flags |
| starting the CLI / FastAPI+MCP server, artifact locations | fastworkflow-run-and-operate |
| what counts as evidence, adding tests | fastworkflow-validation-and-qa |
| pass^k / variance / attribution math | fastworkflow-proof-and-analysis-toolkit |
| running tau2 experiments E0–E25 | tau2-reliability-campaign |
| whether a change is allowed at all | fastworkflow-change-control |
Ground rules (non-negotiable)
- Everything here is read-only. The shipped scripts never write. When a
diagnosis leads you to retrain, train into a temp copy of the workflow —
never let anything (tests, experiments, teardown) touch
fastworkflow/examples/*/___command_info. A training test once destroyed the pre-trained example models other tests silently depended on (the fix-0hb incident, fixed in commit fa97b48). - Never
git commit/pushdiagnostics output or anything else without Dhar's explicit request in that turn (team rule since 2026-07-08). - Use the repo venv interpreter:
.venv/bin/python.import fastworkflowtakes ~5–10 s (pulls dspy/torch); scripts note where that cost applies.
What ships with it
5 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.
- 8d ago First seen · 307 lines · 202 tokens per session scan A 3188cc175aa6
fastworkflow-diagnostics-and-tooling is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 202 tokens to every session and 4,995 once invoked, about $0.0010 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-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.