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 agentmods add skills/bodangren/git-workflow/agent-integratornpx skills add bodangren/git-workflow --skill agent-integratorgit clone --depth 1 https://github.com/bodangren/git-workflowWhat 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 | $0.00054 | $0.01117 |
| Opus 5 | $0.00027 | $0.00558 |
| Sonnet 5 | $0.00011 | $0.00223 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
agent-integrator 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Integrator Skill
Purpose
Idempotently create or update the AGENTS.md file in a project to register AgenticDev skills for discovery by AI agents. This skill ensures that any compatible AI agent working in the repository can discover and use the AgenticDev methodology and available skills.
When to Use
Use this skill in the following situations:
- After running project-init to initialize AgenticDev in a new project
- When installing AgenticDev skills in an existing project
- After adding new skills to the
.claude/skills/directory - Updating the agent guide with new workflow information
- Ensuring AI agents can discover available AgenticDev capabilities
Prerequisites
- Project has
.claude/skills/directory with AgenticDev skills installed - Write permissions to project root directory
- Optional: Existing AGENTS.md file (script creates if missing)
AGENTS.md Purpose
The AGENTS.md file serves as a discovery mechanism for AI agents:
- Agent Discovery: AI agents read this file to learn about available workflows
- Methodology Documentation: Explains AgenticDev philosophy and core principles
- Skill Catalog: Lists all available skills and their purposes
- Getting Started: Provides entry point for new agents working in the project
Workflow
Step 1: Determine If Update Is Needed
Check if AGENTS.md needs to be created or updated:
# Check if file exists
ls -la AGENTS.md
# Check if AgenticDev section exists
grep "SYNTHESIS_FLOW" AGENTS.md
Step 2: Run the Helper Script
Execute the script to update AGENTS.md:
# Use default location (AGENTS.md in project root)
bash scripts/update-agents-file.sh
# Or specify custom location
bash scripts/update-agents-file.sh -f path/to/custom-agents.md
Step 3: Understand What the Script Does
The helper script uses an idempotent update strategy:
- Creates file if missing:
- Uses
touchto ensure target file exists - Safe to run even if file doesn't exist yet
- Uses
What ships with it
2 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.
- 2d ago First seen · 151 lines · 54 tokens per session scan A 57200e5c3aaa
agent-integrator is a skill published in the GitHub repository bodangren/git-workflow (11 stars, last pushed 9mo ago), licensed MIT. It adds 54 tokens to every session and 1,117 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…