tools: Skill for Claude Code

.claude/skills/adopt-pipeline/SKILL.md

adopt-pipeline is a skill for Claude Code from adamw7/tools. It costs 93 tokens per session (3,061 once invoked), scanned A, original, MIT.

A set of instructions for working on an adoption pipeline that adds Claude Code to a GitHub repository and opens a pull request. The pipeline runs ordered steps such as checking tools, cloning, creating a branch, configuring, verifying, and pushing changes.

In plain words
What is it for?
Use it when adding or changing an adoption step, investigating a failed run, or modifying the pipeline's Git, GitHub CLI, or Claude Code integration.
Why use it?
It keeps changes to this real-repository workflow consistent with its step rules, command-line options, credential handling, and safety checks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is adamw7/tools's own configuration. It tells Claude Code how to work on tools itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tools configures →

View source ↗ adamw7/tools
Reuse

Borrowing it

Nothing to install: this file belongs to adamw7/tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/adamw7/tools/main/.claude/skills/adopt-pipeline/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/adamw7/tools

Made for: Claude Code.

Wrote 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.

agentmods badge for adopt-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/adamw7/tools/adopt-pipeline.svg)](https://agentmods.dev/skills/adamw7/tools/adopt-pipeline)
Your own site
<a href="https://agentmods.dev/skills/adamw7/tools/adopt-pipeline"><img src="https://agentmods.dev/badge/skills/adamw7/tools/adopt-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,061 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 46
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 47
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 48
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 62
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 5.1 $0.00093 $0.03061
Opus 5 $0.00046 $0.01530
Sonnet 5 $0.00019 $0.00612
Haiku 4.5 $0.00009 $0.00306

Measured yesterday against content hash cd0e7829d236, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

adopt-pipeline 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 yesterday.

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.

.claude/skills/adopt-pipeline/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adopt Pipeline Skill

Change the adopt module — a pipeline of small, ordered steps that clones a GitHub repository, wires Claude Code into it, and opens a pull request. The module's rules are unusually strict because it shells out to git, gh and claude against real repositories.

The pipeline, in order

GitHubRepoAdopter.defaultSteps(options) assembles:

  1. ToolchainStep — the pipeline's own tools: git, claude, gh (and gh is logged in). Fails before any expensive work. A dry run is checked with ToolchainStep.forDryRun()git and claude only, since gh is used by the pull request the run leaves out.
  2. CloneStep — clones into the workspace, then rewrites the checkout's origin to checkoutUrl(), the same URL without its credentials, so the token git wrote into .git/config does not outlive the run.
  3. BuildToolchainStep — the cloned project's build tool, checked as soon as the clone reveals which one it is.
  4. BranchStep — feature branch (claude/adopt-claude-code by default). The default branch is never written to.
  5. TrustStep — marks the checkout trusted for Claude Code.
  6. ClaudeInitStepClaudeMdConformanceStepCommitStep — generate CLAUDE.md, conform it (plus a companion AGENTS.md) as far as the guard about to be wired in demands — BuildSystem.requiredClaudeMdSections(), so only the Maven path adds the format rule's Java/Maven headings — commit.
  7. EnforcerStepCommitStep — wire the build-tool-aware guard in and commit.
  8. (optional) AssetsStepSkillsStepCommitStep — starter config assets and the starter skills, on --assets, in one commit.
  9. VerifyStep — proves the guard passes on the generated file.
  10. PushStepPullRequestStepomitted entirely on a dry run, so the report says what a dry run really did rather than listing steps that pretended to run.

The build-system-aware steps (BuildToolchainStep, ClaudeMdConformanceStep, EnforcerStep, SkillsStep, VerifyStep) share one BuildSystems.defaults(...) list, so the guard that is wired in is the guard that is verified with the tool that was probed, and the one the starter skills describe (MavenBuildSystem, GradleBuildSystem, FallbackBuildSystem).

Read the full file on GitHub · 194 lines

Files

What ships with it

1 file 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.

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. yesterday Changed cd0e7829d236
  2. 3d ago Changed · +21 lines 645b1ed802ad
  3. 7d ago First seen · 173 lines · 93 tokens per session scan A 7d1735ed9450

Subscribe to this mod's changes

adopt-pipeline is a skill published in the GitHub repository adamw7/tools (11 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 3,061 once invoked, about $0.0005 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.