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-docs-and-positioningnpx skills add radiantlogicinc/fastworkflow --skill fastworkflow-docs-and-positioninggit 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-docs-and-positioning)<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-docs-and-positioning"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-docs-and-positioning.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 5.1 | $0.00171 | $0.05806 |
| Opus 5 | $0.00086 | $0.02903 |
| Sonnet 5 | $0.00034 | $0.01161 |
| Haiku 4.5 | $0.00017 | $0.00581 |
Grade A, and why
fastworkflow-docs-and-positioning 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 6d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fastWorkflow Docs and Positioning
TEAM-PRIVATE: embeds content from uncommitted internal docs. Do not commit or publish this skill without the developer'sexplicit approval.
This skill is the map of every documentation surface in the repo, its authority level, its known rot, the house design-doc process, and the rules for what may be claimed publicly. Facts verified 2026-07-09 against v2.22.2 (commit c33b9a5).
When to use / when NOT to use
Use when you are:
- Editing README, CLAUDE.md, AGENTS.md, anything under
docs/, or the article series - Deciding whether a doc is authoritative, stale, or a ghost (spec for unbuilt feature)
- Making, checking, or citing any external claim (benchmark numbers, paper citation, DOI)
- Starting a design doc, design review, or decision record (use the house template here)
- Touching or referencing the untracked team-private docs in
docs/ - Writing commit messages for docs/design work
Do NOT use for — go to the sibling skill instead:
| Need | Sibling skill |
|---|---|
| Change gating, the non-negotiable rules and their incidents | fastworkflow-change-control |
| Evidence bar for a new experimental result | fastworkflow-research-methodology |
| tau-bench / tau2-bench harness mechanics, pass@1 vs pass^k definitions | fastworkflow-taubench-reference |
| Running the CLI/server, artifact locations | fastworkflow-run-and-operate |
| The tau2 E0–E25 campaign execution | tau2-reliability-campaign |
| Env var / flag catalog | fastworkflow-config-and-flags |
| What counts as test evidence | fastworkflow-validation-and-qa |
1. The docs map, by authority level
"Doc of record" = the file you are allowed to cite as the current truth for its domain. Everything else is rationale archive, marketing, or rot. Full per-file inventory with notes: references/docs-inventory.md.
| Surface | Authority | Audience | Status |
|---|---|---|---|
README.md (603 lines) |
Doc of record for public positioning + quickstart | Public | Live; benchmark provenance gap (§4) |
CLAUDE.md |
Doc of record for agent discipline | Agents | Live; 3 known inaccuracies (§3) |
AGENTS.md |
Doc of record for beads (bd) issue tracking + venv rule |
Agents | Live |
.claude/rules/command-authoring.md |
Doc of record for writing _commands/*.py |
Agents | Live; path-scoped to **/_commands/** and **/context_inheritance_model.json — loads only when touching those paths (moved out of CLAUDE.md in c33b9a5) |
.cursor/rules/testing_rules.mdc |
Doc of record for testing rules | Agents (Cursor) | Live, alwaysApply: true |
fastworkflow-article-1..4.md (repo root) |
Published TUTORIAL series | Public | Live; see name-collision warning (§2) |
docs/*.md (git-tracked) |
Design docs; per-doc supremacy clauses | Team | Mixed — some are ghosts (§3) |
docs/turn_result_design_final.md |
Authoritative spec for TurnResult; explicit "this document wins" clause (lines 1–8) | Team | Live; v3.0 half unimplemented |
fastworkflow/skills_for_coding_fastworkflows/ (integrate-chat-agent + 9 more skills; moved 2026-08-25 from fastworkflow/docs/integrate-chat-agent/) |
Wheel-shipped coding-agent skill library; README calls integrate-chat-agent "the fastest path for a non-trivial app" | Public + downstream devs | Live, ships in the wheel (untracked in git as of the move — commit pending) |
docs/ untracked files |
TEAM-PRIVATE strategy docs (§5) | Team only | NEVER commit without the developer'sexplicit approval |
SECURITY_VULNERABILITY_REPORT.md |
Point-in-time CVE remediation report (2026-01-28) | Team | Historical; one open item (ecdsa CVE-2024-23342, no patch exists). NB the report's own bead reference fastworkflow-d8f (line 86) is absent from .beads/issues.jsonl as of 2026-07-09 — the report has its own rot |
WEC_learning_checklist.md, docs/turn_result_learning_checklist.md |
Mastery checklists (house style, §6) | Team | Living docs |
.cursor/rules/{taskmaster,dev_workflow}.mdc, .windsurfrules, .roo/, .roomodes, .taskmaster/ |
NONE — stale editor-config sprawl | Nobody | Dead since beads adoption; cleanup pending owner decision (§3) |
What ships with it
3 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.
- 6d ago First seen · 290 lines · 171 tokens per session scan A 2c829baa92db
fastworkflow-docs-and-positioning is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed 2d ago), licensed Apache-2.0. It adds 171 tokens to every session and 5,806 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…