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 doordash-oss/agentic-orchestrator --skill revise-roadmapgit clone --depth 1 https://github.com/doordash-oss/agentic-orchestratorWrote 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/doordash-oss/agentic-orchestrator/revise-roadmap)<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/revise-roadmap"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/revise-roadmap/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/doordash-oss/agentic-orchestrator/revise-roadmap"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/revise-roadmap.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 | $0.00009 | $0.02147 |
| Opus 5 | $0.00005 | $0.01073 |
| Sonnet 5 | $0.00002 | $0.00429 |
| Haiku 4.5 | $0.00001 | $0.00215 |
Grade A, and why
revise-roadmap 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 11d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roadmap Revision
Your job is NEVER to write code. Your only deliverable is the revised roadmap markdown inside the output directory.
Output Files
| Artifact | Path | Requirement | Purpose |
|---|---|---|---|
roadmap markdown |
{artifact_dir}/roadmap.md |
required | roadmap markdown matching the create-roadmap format contract |
Critical Rules
- DO re-research the codebase when the critic identifies a wrong claim. If the feedback says "mechanism X doesn't work this way" or "callback Y is already used for Z", read the relevant source file to verify before responding. Do NOT guess or speculate — verify first, then correct.
- Do NOT start from scratch. Read the previous roadmap provided by the user and make targeted edits to address each piece of critic feedback.
- Do NOT rewrite the roadmap if the critic has no substantive changes. If the feedback is purely positive (e.g., "looks good", "approved", no actionable items), simply copy the previous roadmap file to the output directory unchanged.
- Preserve phase intent and sequencing. Phase 1 must keep proving the riskiest integration questions unless the critic explicitly says that sequencing is wrong.
- Preserve explicit stub contracts when they exist. Stubs may be reassigned to different phases, but named stubs from an existing Stub Inventory should not be silently removed. Do not add a stub inventory to roadmaps that intentionally avoid stubs.
- No new unverified claims. When addressing feedback, do NOT introduce assertions that aren't in the design doc or verified against the codebase. This is the #1 cause of revision ping-pong: fixing one reviewer's concern by adding speculation triggers new concerns from the next reviewer.
- Propagate invariant fixes across the whole roadmap. When feedback identifies a rule, owner, or invariant (for example an aggregate-vs-item rule or a completion-owner rule), update EVERY section that mentions that concept: Architecture Approach, What We're NOT Doing, phase goals, Key Tests, exit criteria, and any design-correction notes. Do not patch one section and leave stale contradictory statements elsewhere.
- Delete stale claims instead of layering exceptions on top of them. If an old sentence now contradicts the corrected design, remove or rewrite it. Do NOT keep both and hope the reviewer infers precedence.
- Prefer phased migration language over absolute end-state claims. If the feedback shows that multiple paths still exist today, revise the roadmap to say when centralization completes instead of asserting "X owns all Y" immediately.
- Do NOT re-title or renumber phases listed in any prior sticky
frozen_sections— keep exact heading text byte-equal. Renames break section-matching downstream, invalidate sticky approvals, and force validators to re-evaluate axes they have already cleared. - Do not let revisions grow the roadmap. Prefer narrowing claims over expanding them. If addressing feedback would noticeably increase the roadmap's size, look first for existing detail to remove rather than layering new mechanism details on top.
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.
- 11d ago First seen · 114 lines · 9 tokens per session scan A 6f23f49cb2c9
revise-roadmap is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 9 tokens to every session and 2,147 once invoked, about $0.0000 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…
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…
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…