supervise-agent-pipeline
Supervise a durable multi-phase agent worker, classify execution state, handle bounded approvals and provider fallback, and advance only after validating…
Skill by CraigThomasParsons
Chalk Labs
Need help deploying supervise-agent-pipeline?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/craigthomasparsons-supervise-agent-pipeline
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/supervise-agent-pipeline
What's inside
- Skill name
supervise-agent-pipeline- Description
- Supervise a durable multi-phase agent worker, classify execution state, handle bounded approvals and provider fallback, and advance only after validating structured evidence. Use for tmux workers, phase pipelines, long autonomous runs, stalled workers, or resumable evidence-gated agent handoffs.
- License
- MIT
- Instructions
- 46 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- openai.yaml · agents/
- execution-states.md · references/
- classify_execution.py · scripts/
SKILL.md (first lines)
# Supervise Agent Pipeline Supervise the worker; never become the worker. ## Setup Gather the packet, capability grant, worker adapter, ordered phases, evidence contract, polling cadence, and durable state location. Every phase must have a stable ID and resume boundary. ## Tick Perform exactly one cycle: 1. Capture an adapter-neutral observation: process liveness, activity, approval request, provider error, gate result, receipt reference, and idle streak. 2. Classify it with `scripts/classify_execution.py` or an equivalent deterministic adapter. 3. Take at most one action: - `WORKING`: wait. - `WAITING_APPROVAL`: approve only when the action is explicitly in the grant; otherwise escalate. - `WAITING_PROVIDER`: hand off once to an allowed fallback with identical packet, phase, grant, and evidence requirements. - `BLOCKED_GATE`, `BLOCKED_SCOPE`, `FAILED_INFRASTRUCTURE`: stop and report evidence. - `IDLE`: wait for a second observation. - `STALLED`: inspect process health, then nudge once or restart from the phase boundary. - `DONE`: validate the structured receipt before advancing. 4. Persist the observation, classification, action, and idempotency key. Run the tick from one durable recurring mechanism. Stop it after terminal completion or escalation. ## Phase transition - Start each phase in a fresh context. - Repeat repository, packet, phase, branch, base revision, write surface, prohibited actions, evidence commands, and receipt destination. - Preserve user-authored input in interactive adapters. - Require the worker to write a receipt, then optionally print a short adapter sentinel containing its path and digest. - Do not trust a sentinel until the receipt validates. - Return to `$coordinate-cross-project-work` when the packet phase completes. ## Tmux adapter lessons - Type and submit in separate operations so prompts can be verified before execution. - Treat subagent-wait markers as working, not idle. - Require two idle observations before declaring a stall. - Detect a dead worker process before nudging. - Keep tmux scrollback observational; durable protocol state belongs outside the pane. Read [references/execution-states.md](references/execution-states.md) for classification precedence.
From CraigThomasParsons/TheGiteaCodeFactory, MIT.
More from CraigThomasParsons/TheGiteaCodeFactory
- 0.586score
tmux-pipeline
CraigThomasParsons
Execute one issue in isolated worktrees through implementation, simplification, architecture, review and PR phases.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
improve-codebase-architecture
CraigThomasParsons
Find architectural friction in a change set, evaluate module depth and test boundaries, and apply worthwhile scoped refactors in a pipeline architecture phase.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
dispatcher
CraigThomasParsons
Select a dependency-ready feature slice, audit BDD coverage, and prepare issue-backed work packets.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
pr-review-resolve-loop
CraigThomasParsons
Review and repair bounded Gitea PR batches and merge only current-head cleared PRs under the project merge policy.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
slice-pipeline
CraigThomasParsons
Deliver an issue-backed feature slice through serial tmux phases with durable evidence and resumable supervision.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
simplify
CraigThomasParsons
Simplify an issue's changed code without changing behavior, then verify and push the scoped cleanup.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
scrum-master
CraigThomasParsons
Supervise issue-backed delivery, identify stalled work and blockers, and reconcile queue progress.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
coordinate-cross-project-work
CraigThomasParsons
Plan dependency-ordered repository work and reconcile cross-project evidence without editing product repositories.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
moonlighter
CraigThomasParsons
Coordinate factory work through Moonlighter intake and authoritative job claims.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
pr-resolve-loop
CraigThomasParsons
Repair current-revision Gitea PR findings and request independent re-review.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
pr-review-resolver
CraigThomasParsons
Address human feedback on an existing PR branch and draft replies without posting them.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
release-preparation
CraigThomasParsons
Prepare an evidence-backed GitHub mirror and draft release for a completed Gitea milestone.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 3
- Last commit (this folder)
- Oct 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from CraigThomasParsons
- 0.586score
tmux-pipeline
CraigThomasParsons
Execute one issue in isolated worktrees through implementation, simplification, architecture, review and PR phases.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
improve-codebase-architecture
CraigThomasParsons
Find architectural friction in a change set, evaluate module depth and test boundaries, and apply worthwhile scoped refactors in a pipeline architecture phase.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
slice-pipeline
CraigThomasParsons
Deliver an issue-backed feature slice through serial tmux phases with durable evidence and resumable supervision.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
dispatcher
CraigThomasParsons
Select a dependency-ready feature slice, audit BDD coverage, and prepare issue-backed work packets.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
pr-review-resolve-loop
CraigThomasParsons
Review and repair bounded Gitea PR batches and merge only current-head cleared PRs under the project merge policy.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
simplify
CraigThomasParsons
Simplify an issue's changed code without changing behavior, then verify and push the scoped cleanup.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get supervise-agent-pipeline running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
supervise-agent-pipeline skill. Agent Mart. https://agentmart.dev/skills/craigthomasparsons-supervise-agent-pipeline (last updated 2026-10-24)