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/john-wilmes/claude-agentic-coding-playbook/learnnpx skills add john-wilmes/claude-agentic-coding-playbook --skill learngit 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/learn)<a href="https://agentmods.dev/skills/john-wilmes/claude-agentic-coding-playbook/learn"><img src="https://agentmods.dev/badge/skills/john-wilmes/claude-agentic-coding-playbook/learn.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.01262 |
| Opus 5 | $0.00026 | $0.00631 |
| Sonnet 5 | $0.00010 | $0.00252 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
learn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn
Capture a lesson as a structured knowledge entry that persists across sessions and projects.
Steps
Install Root Discovery
INSTALL_ROOT=$(bash ~/.claude/scripts/skills/find-install-root.sh)
0. Check prerequisites
Check if knowledge-db.js is available:
ls ${INSTALL_ROOT}/.claude/hooks/knowledge-db.js 2>/dev/null
If not found, fall back to writing the lesson directly to the project memory file (lessons-learned.md in the project memory directory). Skip steps that reference knowledge-db.js and instead append the structured entry to the memory file using the Edit tool.
1. Identify the lesson
If $ARGUMENTS is provided, use it as the lesson description. Otherwise, review what happened in the current session and ask the user what they want to capture.
Skip trivial or session-specific facts. Good candidates:
- Non-obvious bugs and their root causes
- Workarounds for tool or platform issues
- Patterns that save significant time
- Configuration gotchas that cause silent failures
- Security issues encountered
2. Classify the entry
Based on the lesson, determine:
Category (pick one):
gotcha— surprising behavior, silent failure, or common mistakepattern— reusable approach or best practiceworkaround— temporary fix for a known issueconfig— configuration requirement or settingsecurity— security-related findingperformance— optimization or bottleneck insightconvention— project-specific conventions, coding standards, naming patterns, or workflow preferences that should be remembered for future sessions in the same projectreference— factual reference information: API endpoints, config keys, schema details, version constraints, or external service behaviorsdecision— architectural or design decisions with rationale; records why a particular approach was chosen over alternatives, to prevent re-debating settled questions
Tool: The primary tool, library, or platform (e.g., git, npm, docker, amplify, vitest).
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.
- 5d ago First seen · 140 lines · 51 tokens per session scan A ac114680c530
learn is a skill published in the GitHub repository john-wilmes/claude-agentic-coding-playbook (4 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,262 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 2026-08-31.
Other skills, from other repositories
save-progress
Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.