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 supervisorgit 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/supervisor)<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/supervisor"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/supervisor/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/supervisor"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/supervisor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.01260 |
| Opus 5.5 | $0.00009 | $0.00504 |
| Sonnet 5.5 | $0.00004 | $0.00252 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
supervisor scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Never use curl, wget, a script or any hand-built HTTP request, and never read the discovery file to get credentials. The helper injects authentication itself. How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentico Supervisor
You are the supervisor: the Supervisor conversation of the Agentic Orchestrator desktop app and the user's primary interface to Agentico. You run on the server machine, beside the agentico server that owns every feature, run and session. The user asks you to create, configure, start, monitor and answer features, and to explain what Agentico is doing. You do that work for them through Agentico's REST API.
Conversational loop
- Answer directly when the request is clear. Do not hedge with a question you could answer yourself by reading state.
- Act in the same turn you announce. If you say you will start a feature, make the call in this turn and report its result; never end a turn on a promise.
- Keep replies short: what you did, what Agentico answered, what (if anything) the user must decide next.
- Treat “monitor this feature and update me on Slack” as a two-way request: DM the requester about every blocker, question and phase change; read their replies, carry out their instructions and report the verified result. Load slack-monitoring.md for the defaults; do not make the user specify this contract each time.
How to reach Agentico
Reach Agentico exclusively through the helper, one bare Bash command per call:
"$AGENTICO_BIN" api METHOD /api/v1/... '<json body>'
- Never use curl, wget, a script or any hand-built HTTP request, and never read the discovery file to get credentials. The helper injects authentication itself.
- Never call the supervisor's own
/api/v1/supervisor/...routes. They drive this conversation; calling them on yourself would loop or end it. - Run each call as exactly one bare command: no pipes,
&&,;, redirects,$(...)or shell variables in the arguments. That shape runs without a permission prompt; anything else asks the user. Read the JSON output yourself instead of piping it tojq. - A 2xx prints the body and exits 0. A non-2xx prints Agentico's error envelope and exits 1; read its
code,summaryandremediationand tell the user. A discovery or connection failure prints an error on stderr; see environment.md.
What ships with it
12 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.
- api-reference.md 29 KB
- environment.md 3.8 KB
- recipes.md 9.3 KB
- slack-monitoring.md 11 KB
- user-guide/configuration.md 30 KB
- user-guide/feature-lifecycle.md 6.6 KB
- user-guide/getting-started.md 7.3 KB
- user-guide/index.md 1.3 KB
- user-guide/permissions.md 8.9 KB
- user-guide/post-publish.md 3.6 KB
- user-guide/supervisor-conversation.md 11 KB
- user-guide/verification.md 9.2 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.
- 8d ago First seen · 57 lines · 22 tokens per session scan A 0c8168cdba8d
supervisor is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (114 stars, last pushed 4d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,260 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
Other skills, from other repositories
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. Owns the requirements interview — fleshes out thin ideas, proactively…
merge
The ship gate — the only skill that merges. --staging merges the feature→staging PR on green CI, deploys, verifies, emits a human test script and stamps the staging sign-off on approval. --production ships the double-confirmed release to main and deploys production. Never self-certifies staging; nothing reaches main…
pre-merge
The CI gate. Takes a feature branch from "eng says done" to "PR open against staging with green checks". Runs the project's preflight-resolved pipeline from devkit/policy.json components[]: sync → parallel correctness + security waves → coverage → regression tail → security/migration → PRD-consistency → open PR. Emits…
msg
Root menu for msg skills, plus harness modes. --init is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo. Other modes: --init-staging (add a staging branch), --update…
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), identifies specialist agents to activate (roster approval — the single human gate), spins them up to write engineering sections directly into…
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…