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 digital-stoic-org/agent-skills --skill pick-workflowgit clone --depth 1 https://github.com/digital-stoic-org/agent-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/digital-stoic-org/agent-skills/pick-workflow)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/pick-workflow"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/pick-workflow.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00156 | $0.01715 |
| Opus 5 | $0.00078 | $0.00857 |
| Sonnet 5 | $0.00031 | $0.00343 |
| Haiku 4.5 | $0.00016 | $0.00171 |
Grade A, and why
pick-workflow 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pick Workflow
Authoring-time judge for a skill/agent's execution topology: how steps run (linear vs fan-out, which mechanism, where the seam falls). Emits a design — never runs the task. Model+effort per step is a separate call, delegated (Step 5). Own the topology decision here; don't re-derive the mechanism table or the sharding rules anywhere else.
When: authoring or challenging a skill/agent · parallel-vs-linear · which delegation mechanism.
Steps
1. Decompose — fill the table FIRST (it IS the analysis; no recommending before it exists)
| Step | Work shape | Parallelizable? | Judgment load | Token weight | Cross-item dep? |
|---|
- Work shape — read / classify / synthesize / transform / decide.
- Parallelizable? — units independent? (per-file yes; "synthesize the whole plan" no.)
- Judgment load — low (mechanical/schema-bound) → high (ordering, trade-offs, reversibility, intent).
- Token weight — where cost sits (usually the step that reads everything).
- Cross-item dep? — compares across units / needs the global graph? Correctness gate: a cross-item step must NOT be sharded. Two gates + worker rules in
reference.md.
2. Cut the seam by global-context (NOT by folder/file)
Fan out per-item, judgment-light, independent work → workers return structured facts only (no
dispositions/severity/decisions). Keep cross-item reasoning + dispositions + synthesis on the
orchestrator. Canonical: gather (fan-out) → reason → plan (orchestrator) → execute (fan-out independent ops).
If the execute fan-out writes, isolate each worker (isolation: "worktree") or give it unique paths —
concurrent edits to one tree lose updates with no error.
3. Pick topology + mechanism
Front-door first (pattern catalog in reference.md): routing (distinct input kinds → branch before
fan-out) · voting / evaluator-optimizer (need confidence or refinement). Then:
| Choose | When | Gate |
|---|---|---|
| 🟢 Linear | below threshold; few units — the default | simplest |
| 🔵 Sub-agents (fresh ctx) | fixed small set (2–6) independent tasks; worker needs a scoped brief, not your history. Name them: messaging a finished worker by name replays its whole transcript, so refine loops live here | blind to each other → dedup/merge stays on the orchestrator · caps in reference.md |
| 🍴 Fork | one heavy sub-task needing your full accumulated reasoning, run isolated so its tool noise stays out of main | inherits parent bias → never for verify/challenge |
| 🧑🤝🧑 Team (named teammates + shared task list) | workers must reason against each other: debate, competing hypotheses, cross-worker dedup with no barrier | env-gated · token-heavy · 3–5 · no nesting · same-file edits collide |
| 🟣 Workflow | fan-out over a variable-size list; loop-until-dry, budget cap, schema extraction, journaled resume | two barriers: user opt-in AND stripped from every sub-agent → never a default; ship a linear fallback |
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.
- 8d ago First seen · 99 lines · 156 tokens per session scan A fe84ea9d65d0
pick-workflow is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 2d ago), licensed MIT. It adds 156 tokens to every session and 1,715 once invoked, about $0.0008 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…