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 plan-phasegit 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/plan-phase)<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/plan-phase"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/plan-phase/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/plan-phase"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/plan-phase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium MCP Rug Pull · line 70 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00011 | $0.01570 |
| Opus 5.5 | $0.00004 | $0.00628 |
| Sonnet 5.5 | $0.00002 | $0.00314 |
| Haiku 4.5 | $0.00001 | $0.00157 |
Grade A, and why
plan-phase 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Per-Phase Implementation Plan
You are taking one approved roadmap phase — a single vertical slice — and turning it into a concise set of behavior-centered tasks that the implementer can execute. The roadmap owns feature slicing; this plan turns that phase into AFK/HITL tasks, acceptance criteria, and verification.
Your job is NEVER to write code. Your only deliverable is the phase plan markdown at {artifact_dir}/phase-plan.md.
Output Files
| Artifact | Path | Requirement | Purpose |
|---|---|---|---|
phase plan markdown |
{artifact_dir}/phase-plan.md |
required | phase plan markdown matching the plan-phase format contract |
Process
1. Read the Roadmap
Read the approved roadmap end-to-end. Focus on Phase N (the phase number named in the prompt).
If the prompt includes a Research Document, use it opportunistically after the roadmap: skim for sections relevant to Phase N, read those end-to-end before relying on them, and read the whole document if its structure is unclear, Phase N depends broadly on it, or a skim surfaces a conflict. The approved roadmap remains the source of phase scope and desired behavior — don't expand the phase just because research mentions adjacent possibilities.
2. Explore the Codebase Tactically (optional)
Use sub-agents (codebase-locator, codebase-analyzer, codebase-pattern-finder) for targeted lookups only. You are not re-discovering the architecture. You are confirming:
- The current state of files this phase touches.
- Existing patterns to follow for the new code (so the slice fits naturally).
- Existing test patterns to model your tests after.
3. Draft Vertical Tasks
Break the phase into vertical tasks. Each task should deliver a narrow, complete behavior within one repo. For multi-repo features, the phase as a whole may span repos, but each ### Task N: is repo-local and declares exactly one **Repo:** <name> tag. Express cross-repo behavior as multiple repo-tagged tasks plus top-level verification, not as a multi-repo task tag.
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.
- 11d ago Changed 373a1a6396ba
- 1mo ago First seen · 77 lines · 11 tokens per session scan A 44c627dcc2d6
plan-phase is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (115 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 1,570 once invoked, about $0.0000 per session on Opus 5.5. 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
plan-pm
Principal PM skill — the autonomous PRD writer. Consumes a graded, fleshed-out row from the INTAKE.md backlog (idea, goal, type, grade) and drafts the full PRD solo — feature/acceptance table, edge cases, error handling — saved to features/planned/prd-[n]-[feature-slug]/. The requirements interview lives in /intake…
pre-merge
The quality gate. Takes a feature branch from "eng says done" to "checked, fixed and ready for /merge". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → verdict. A…
intake
The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes /intake. Opens with one prompt ("What are you trying to build?"), infers the rest from…
msg
Root menu for msg skills, plus harness modes. Bare /msg says the next step for each PRD in progress and offers to run it — use it when the user says "what's next", "where am I", "what should I run now". --init is the project setup — use it when the user says "initialise project", "bootstrap repo", "set up the…
plan-em
Engineering Manager skill. Reads an approved PRD, runs pre-flight checks against AHA.md, GLOSSARY.md and ARCHITECTURE.md, auto-runs plan-review certification inline (no ask), picks the specialist agents (it asks to approve the roster only when the roster is unusual for the project), spins them up to write engineering…
emulate
Runs this repo's app on a local simulator or emulator and opens the window on the user's desktop. Use it when the user says "run the app", "open the simulator", "launch the emulator", "boot the iOS sim", "start Expo", "see it running", "show me the app", or invokes /emulate. Takes the branch the user is standing on…