Tokenman — Data skill for Claude Code
A self-evolving scaffold for autonomous web projects.
How to install Tokenman
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open verkyyi/tokenman and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Tokenman does
A self-evolving scaffold for autonomous web projects. 9 workflows, hourly self-evolution, self-healing pipeline, feedback learning loop. The repo is the system.
Alternatives in Data
- OpenViking — Self-evolving Context Database for AI Agents 33.3k ★
- User Segmentation — Segment users by behavior, JTBD, and needs from feedback data 7.8k ★
- Autonovel — An autonomous novel writing pipeline, by Hermes Agent 1.5k ★
README
Tokenman
Tokenman is a thin control layer for Claude inside GitHub Actions.
The MVP is intentionally narrow:
- one job:
docs_maintainer - one runtime: GitHub Actions
- one trust boundary: explicit
read_pathsandwrite_paths - three outcomes: pull request, issue, or no-op
Claude does the reasoning and editing. Tokenman supplies the fixed job, prompt shaping, scope enforcement, output routing, run artifacts, and append-only history.
MVP contract
The public surface is the GitHub Action at [action.yml](action.yml). It accepts:
github_tokenread_pathswrite_pathsjob_typedefaultdocs_maintaineron_high_confidencedefaultpull_requeston_low_confidencedefaultissue
Tokenman runs Claude against the checked-out repo, validates the diff, and then:
- opens a PR when the edit is in-scope
- opens an issue when the run is blocked or confidence is low
- records a no-op when nothing useful changed
Example
name: Tokenman Docs Maintainer
on:
push:
branches:
- main
paths:
- "services/payments/**"
- "openapi/payments.yaml"
workflow_dispatch:
jobs:
docs-maintainer:
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
issues: write
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Run Tokenman
uses: your-org/tokenman@v1
env:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
read_paths: |
services/payments/**
openapi/payments.yaml
write_paths: |
docs/payments/**
on_high_confidence: pull_request
on_low_confidence: issue
`ANTHROPIC_API_KEY` is shown above because Tokenman wraps the official Claude Code Action, which needs model authentication for automation runs. You can also provide `CLAUDE_CODE_OAUTH_TOKEN` instead.
Rep
Related Skills
Brightdata Scraper Studio Skill
Claude Code skill for building, running and self-healing Bright Data Scraper Studio web scrapers from the term
Multi Agent Evolution Framework
Multi-Agent Coding Orchestration Framework, Governed, CLI-agnostic, with HarnessX inspired gated in-process to
Claude Booster
Self-installing memory + quality system for Claude Code. Rolling memory DB, multi-agent pipeline (тройка), mod
Siddhi
SIDDHI: The first desktop computer-use agent with a runtime self-evolving skill pipeline. Autonomously promote
Openclaw Self Evolving
2+ Weekly self-improvement pipeline — scans Claude Code logs, proposes CLAUDE.md/AGENTS.md rule changes, zero
Self Eval
Self-improvement loop. After a pipeline run, reviews how faithfully it executed step-by-step (from the determi
Related Agents
n8n Debugger
n8n workflow debugger with self-healing loop. Use PROACTIVELY when user reports workflow errors, failed execut
Fpm Orchestrator
Master agent for FangPostMeet pipeline. Coordinates 6 sub-agents to process recordings end-to-end. Two phases
Game QA
Game QA. Runs the autonomous self-verify loop (build → launch .exe → screenshot → read PNG → verdict). Catches