supervisor-session

A session workflow for coordinating several coding agents through a supervisor. The supervisor researches the codebase, fixes interfaces and work boundaries, assigns separate tasks, checks the results, and handles shared-file changes.

In plain words
What is it for?
Use it to plan and supervise multi-agent coding work, including codebase research, parallel implementation, review, testing, and final integration.
Why use it?
It reduces conflicts when multiple agents work on the same project and provides checkpoints for verifying that their changes match the agreed design.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/agentproto/ts/supervisor-session
Any agent
npx skills add agentproto/ts --skill supervisor-session
Clone the repo
git clone --depth 1 https://github.com/agentproto/ts

Made for: Claude Code, Codex.

Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,269 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00195 $0.03269
Opus 5 $0.00097 $0.01635
Sonnet 5 $0.00039 $0.00654
Haiku 4.5 $0.00019 $0.00327

Measured 2d ago against content hash b2bf6d6b44cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

supervisor-session 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 2d 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.

packages/skill-pack-agentproto/src/skills/supervisor-session/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Supervisor session (agentproto)

Principle: the supervisor holds the plan, the contracts, and the disk truth; the sessions hold the work. You do not code — EXCEPT for consolidation and surgical fixes (1 file, known cause), because the worktree is local: that is what "keeping the ability to act" means.

Pipeline (roles → artifacts)

scout (1M-ctx model, cheap)       → recon doc VERIFIED against source (spot-check grep it yourself)
you                               → SPEC.md + FROZEN interface contract + per-WP file matrix
parallel executors (cheap)        → WPs on DISJOINT scopes (briefs = .plans/ files)
you (after each turn-end)         → disk verification + targeted checkpoint commit
you (single writer)               → consolidation (shared files: extension.ts, package.json…)
verify session (Sonnet, sub)      → re-run gates + adversarial review of the diff (does not fix, reports)
you                               → LIVE e2e (tsx script against the real daemon) + PR (cf. the repo's AGENTS.md)
  • WP0 foundation first, alone: it FREEZES the interfaces (client, store, command ids). WP1..N code against those names without coordinating.
  • Shared files belong to nobody. Each brief forbids package.json / extension.ts (and equivalents) and requires in the final report: the exact wiring lines + config snippets to merge. Consolidation (you) applies them in one pass and resolves collisions (e.g. two WPs claiming the same command → rename one).
  • Briefs = files in .plans/<project>/WPn-brief.md; the session prompt contains ONLY the pointer + the overrides (no-git, no-subagents, parallel- aware). Mandatory final report: files touched, design choices, wiring lines, REAL exit codes.

Preflight (before any spawn)

  1. Load the TARGET repo's agent-instructions file (not this one) — "done" is declared there, never here (same discipline as in End of session: this skill points, it does not restate).
  2. auth_profile_list + adapter_list BEFORE any spawn: choose the executor's auth from the profile's METHOD — a gateway provider (openrouter, moonshot) wants an api-key profile (access.profileRef), never auth:{mode:"subscription"} (reserved for Anthropic/claude-code). Billing fallback when a provider is dead/flaky: OpenRouter cheap → claude-sdk moonshot (kimi) → claude-code subscription + cheap Anthropic (haiku), zero marginal cost. Never block the pipeline on a dead provider.

Read the full file on GitHub · 215 lines

Changes

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.

  1. 2d ago First seen · 215 lines · 195 tokens per session scan A b2bf6d6b44cf

Subscribe to this mod's changes

supervisor-session is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 195 tokens to every session and 3,269 once invoked, about $0.0010 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 2026-08-31.

Related

Other skills, from other repositories

strands-review

Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…

strands-agents/harness-sdk · 125 tokens

docs-writer

Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…

strands-agents/harness-sdk · 74 tokens

pr-create

Creates a GitHub pull request using the gh CLI. Use when the user asks to create, open, or submit a PR on GitHub.

strands-agents/harness-sdk · 32 tokens

document-service

This skill should be used when the user asks to "analyze this codebase", "document this service", "generate technical docs", "I inherited this code", "help me understand this system", "create docs for this project", "what does this system look like", "onboard me to this codebase", "this codebase has no docs"…

awslabs/agent-plugins · 141 tokens

aws-step-functions

Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS service integration, and migrating from the JSONPath to the JSONata query language.

awslabs/agent-plugins · 57 tokens

hyperpod-version-checker

Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…

awslabs/agent-plugins · 120 tokens