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 kishorkukreja/awesome-supply-chain --skill supply-chain-decision-to-delegationgit clone --depth 1 https://github.com/kishorkukreja/awesome-supply-chainWrote 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/kishorkukreja/awesome-supply-chain/supply-chain-decision-to-delegation)<a href="https://agentmods.dev/skills/kishorkukreja/awesome-supply-chain/supply-chain-decision-to-delegation"><img src="https://agentmods.dev/badge/skills/kishorkukreja/awesome-supply-chain/supply-chain-decision-to-delegation/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/kishorkukreja/awesome-supply-chain/supply-chain-decision-to-delegation"><img src="https://agentmods.dev/badge/skills/kishorkukreja/awesome-supply-chain/supply-chain-decision-to-delegation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00084 | $0.03017 |
| Opus 5 | $0.00042 | $0.01509 |
| Sonnet 5 | $0.00017 | $0.00603 |
| Haiku 4.5 | $0.00008 | $0.00302 |
Grade A, and why
supply-chain-decision-to-delegation 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 9d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supply Chain Decision to Delegation
Turn an operational symptom into a decision that can be understood, measured, and delegated responsibly. This is a diagnostic and facilitation workflow, not an AI idea generator. A valid outcome may be not ready for AI.
Operating contract
Follow these rules throughout the session:
- Begin with a real operating moment, not a technology request. Ask for a recent example of the scramble, exception, delay, shortage, imbalance, or recurring decision.
- Do not recommend an agent until the trigger, decision, owner, evidence, time window, stakes, reversibility, and consequences are explicit.
- Separate three kinds of work: establishing facts, comparing options, and making or releasing a consequential commitment.
- Treat business accountability as human or organisational. AI may prepare, recommend, or execute inside approved rules; it does not own customer, commercial, safety, regulatory, or operational consequences.
- Surface missing ownership, unreliable data, policy ambiguity, and unresolved cross-functional conflict. Do not hide them inside an AI proposal.
- Use qualitative gates by default. Do not invent numerical scores, benefits, probabilities, or return on investment.
- Preserve the user's terminology while tightening vague labels into testable statements.
- If the use case is not ready, say so plainly and produce the not-ready output instead of forcing a pilot.
Choose a session mode
Infer the lightest mode that can produce a defensible result. Tell the user which mode you are using.
- Quick framing: One pain point, one decision, and a concise brief. Use when the user has a concrete example and a known owner.
- Deep diagnosis: A guided interview that tests ownership, evidence, stakes, reversibility, consequences, and readiness. Use when the problem is vague, cross-functional, or high stakes.
- Use-case shortlist: Compare several candidate decisions and recommend one bounded starting point. Use when the user has multiple opportunities or a transformation backlog.
- Workshop facilitation: Structure a leadership or planning-team discussion, record disagreements, and produce an agreed brief. Use when several functions share the workflow or consequences.
What ships with it
14 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.
- agents/openai.yaml 342 B
- output-templates/bounded-pilot-charter.md 2.0 KB
- output-templates/decision-to-delegation-brief.md 2.4 KB
- output-templates/not-ready-report.md 1.2 KB
- output-templates/problem-statement-canvas.md 1.4 KB
- output-templates/use-case-shortlist.md 1.2 KB
- output-templates/workshop-summary.md 1.4 KB
- references/delegation-boundaries.md 6.1 KB
- references/facilitation-guide.md 8.0 KB
- references/governance-and-evidence.md 4.0 KB
- references/problem-framing.md 7.9 KB
- references/related-skills-map.md 4.3 KB
- references/use-case-selection.md 5.7 KB
- references/worked-example.md 6.5 KB
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.
- 9d ago First seen · 243 lines · 84 tokens per session scan A af032241cd13
supply-chain-decision-to-delegation is a skill published in the GitHub repository kishorkukreja/awesome-supply-chain (67 stars, last pushed 12d ago), licensed MIT. It adds 84 tokens to every session and 3,017 once invoked, about $0.0004 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 2026-09-03.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…