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 agentmods add skills/radiantlogicinc/fastworkflow/fastworkflow-debugging-playbooknpx skills add radiantlogicinc/fastworkflow --skill fastworkflow-debugging-playbookgit 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-debugging-playbook)<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-debugging-playbook"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-debugging-playbook.svg" alt="Measured on agentmods" 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 | $0.00210 | $0.08167 |
| Opus 5 | $0.00105 | $0.04084 |
| Sonnet 5 | $0.00042 | $0.01633 |
| Haiku 4.5 | $0.00021 | $0.00817 |
Grade C, and why
fastworkflow-debugging-playbook scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| T9 | LLM outputs look frozen — refine/agent/param-extraction returns identical answers despite prompt/code changes | DSPy disk/memory cache serving stale completions | Delete or disable the cache and re-run; if output How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TEAM-PRIVATE: embeds content from uncommitted internal docs. Do not commit or publish this skill without the developer'sexplicit approval.
fastWorkflow Debugging Playbook
Runbook for diagnosing fastWorkflow failures. Written against v2.22.2 (commit c33b9a5). Every file:line below was verified against that tree; re-verification one-liners are in Provenance and maintenance.
When to use / when NOT to use
Use when something is broken and you need symptom → cause → discriminating experiment → fix.
Do NOT use — go to a sibling instead:
| Need | Sibling skill |
|---|---|
| Full incident chronicles (root cause + evidence + status) | fastworkflow-failure-archaeology |
| What every env var / CLI flag does | fastworkflow-config-and-flags |
| How to run CLI/examples/FastAPI server normally | fastworkflow-run-and-operate |
| Measurement scripts and interpretation guides | fastworkflow-diagnostics-and-tooling |
| Intent/param-extraction internals (models, thresholds, DSPy) | fastworkflow-nlu-pipeline-reference |
| Adding tests, what counts as evidence | fastworkflow-validation-and-qa |
| Change gating / non-negotiables before you fix anything | fastworkflow-change-control |
| tau2/tau-bench experiment work (E0–E25) | tau2-reliability-campaign |
Jargon (defined once)
- Workflow: a directory with
_commands/*.pycommand files; fastWorkflow wraps your app with it. - CME: the internal
command_metadata_extractionworkflow (infastworkflow/_workflows/) that runs intent detection + parameter extraction as a pseudo-command namedwildcard. Every session owns a private CME workflow instance. - WEC:
WorkflowExecutionContext(fastworkflow/workflow_execution_context.py) — the transport-free execution core. One user message in, one turn out. - Topology A / B: A = CLI
ChatSessionwith queues + a worker thread (blockingask_user); B = bare WEC embedded by FastAPI (ask_usersuspends and resumes on the next message). ___command_info/: per-workflow trained artifacts —command_directory.json,routing_definition.json,<cmd>_param_labeled.json, and per-context model folders (tinymodel.pth/,largemodel.pth/,label_encoder.pkl,threshold.json).___convo_info/: per-workflow runtime NLU caches (learned utterance→command mappings, suggested commands) in RocksDB (speedict.Rdict) files.- Fingerprint: sha256 over the set of
(path, size, mtime_ns)of all command sources, stamped into the two JSON artifacts (v2.22.1) so stale snapshots are rebuilt. - NOT_FOUND: sentinel string (from env var
NOT_FOUND) meaning "parameter not extracted yet"; extraction control-flow branches on it. - DSPy: LLM-programming library used for parameter extraction and the agent; it caches LLM calls on disk (
~/.dspy_cachefor dspy 3.2.1).
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.
- 4d ago First seen · 341 lines · 210 tokens per session scan C 7d12baecf045
fastworkflow-debugging-playbook is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed today), licensed Apache-2.0. It adds 210 tokens to every session and 8,167 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…