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 skills add john-wilmes/claude-agentic-coding-playbook --skill playbookgit clone --depth 1 https://github.com/john-wilmes/claude-agentic-coding-playbookWrote 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.
[](https://agentmods.dev/skills/john-wilmes/claude-agentic-coding-playbook/playbook)<a href="https://agentmods.dev/skills/john-wilmes/claude-agentic-coding-playbook/playbook"><img src="https://agentmods.dev/badge/skills/john-wilmes/claude-agentic-coding-playbook/playbook/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/john-wilmes/claude-agentic-coding-playbook/playbook"><img src="https://agentmods.dev/badge/skills/john-wilmes/claude-agentic-coding-playbook/playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.01715 |
| Opus 5.5 | $0.00028 | $0.00686 |
| Sonnet 5.5 | $0.00014 | $0.00343 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
playbook scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playbook Configurator
Analyze the user's Claude Code configuration and intelligently merge playbook best practices. Unlike the install script's --wizard mode (which does simple file-level skip/overwrite/backup), this skill understands the semantic content of CLAUDE.md files and merges section-by-section.
Install Root Discovery
Before running any mode, determine where the playbook's .claude/ directory is installed. The install root may differ from ~/.claude/ if the user ran install.sh --root <path>.
Run the install-root discovery helper:
INSTALL_ROOT=$(bash ~/.claude/scripts/skills/find-install-root.sh)
All <INSTALL_ROOT> references below use this resolved path.
Modes
Parse $ARGUMENTS to determine the mode:
global(default if no argument): Analyze and improve<INSTALL_ROOT>/.claude/CLAUDE.mdproject: Analyze and improve the current project'sCLAUDE.mdcheck: Audit current configuration and report what is missing or outdated
Steps for global mode
1. Read the user's global CLAUDE.md
Read <INSTALL_ROOT>/.claude/CLAUDE.md. If it does not exist, offer to create one from scratch using the playbook template.
2. Analyze existing sections
Identify the sections in the user's file. Map them to the playbook's recommended sections:
Playbook recommended sections:
- The Workflow (Explore, Plan, Code, Verify, Commit)
- Reasoning Standards (evidence-based debugging, hypothesis-driven, cite sources)
- Efficiency and Cost Optimization (parallel calls, no re-reads, model routing)
- Context and Session Management (fresh sessions, /compact, subagents)
- Quality Gates (type-check, lint before commit)
- Testing and Verification (lowest-level tests, continuous feedback loop)
- Code Review (automated review on every commit)
- Security (no credentials, sandbox mode, MCP server restrictions)
- Git Discipline (no --no-verify, no force-push)
- File Creation Rules (no orphan files, no one-off scripts)
- Memory File Discipline (Current Work tracking, lessons learned)
- Repository Hygiene (.gitignore, no large files)
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.
- 1mo ago First seen · 191 lines · 70 tokens per session scan A 28c88de25ec1
playbook is a skill published in the GitHub repository john-wilmes/claude-agentic-coding-playbook (4 stars, last pushed 6mo ago), licensed MIT. It adds 70 tokens to every session and 1,715 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
rust-skills
Comprehensive Rust coding guidelines with 265 rules across 26 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, concurrency, unsafe code, API design, memory optimization, performance, numeric safety, conversions, serde, pattern matching, macros…
plan-feature
Turn a rough feature idea into a written specification by interviewing the user first. Use when the user describes something substantial they want built and the approach is not yet settled.
harness-init
Bootstrap project entry docs and evidence-backed feature catalogs with one confirmation. Reuse existing documentation owners; no Node/npm required.
pipeline-quality-audit
Audit and improve media or AI-generation pipelines whose command may succeed while the delivered output is unusable. Use direct output evidence, attempt automatic repair/retry/fallback, quarantine bad attempts for diagnosis, and stop only when no valid deliverable can be produced.
fix-issue
Resolve a GitHub issue end to end, from reading the issue through to opening a pull request. Use when the user names an issue number to fix.
review-pr
Review a pull request for correctness, architecture, security, and test coverage. Use when the user names a PR number to review.