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 promotegit 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/promote)<a href="https://agentmods.dev/skills/john-wilmes/claude-agentic-coding-playbook/promote"><img src="https://agentmods.dev/badge/skills/john-wilmes/claude-agentic-coding-playbook/promote.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 | $0.00053 | $0.00915 |
| Opus 5 | $0.00026 | $0.00458 |
| Sonnet 5 | $0.00011 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
promote scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote
Promote a lesson from this project's memory to global scope so it applies to all future projects.
Steps
Install Root Discovery
INSTALL_ROOT=$(bash ~/.claude/scripts/skills/find-install-root.sh)
1. Find project lessons
Read the project's MEMORY.md file. It is located in the Claude Code auto-created project memory directory. To find it:
# The path is derived from the working directory
ls ${INSTALL_ROOT}/.claude/projects/*/memory/MEMORY.md 2>/dev/null
Pick the one that corresponds to the current project (match the encoded project path in the directory name).
Extract the ## Lessons Learned section. Collect each lesson as a candidate.
If $ARGUMENTS is provided and is not "list", use it directly as the lesson text — skip to step 3.
2. Present candidates
Show the lessons found, numbered:
Lessons found in project memory:
1. <lesson 1>
2. <lesson 2>
...
Which lesson would you like to promote to global scope? (enter number or paste text)
Wait for the user to select one. If there is only one lesson, proceed with it automatically.
If no lessons section exists, tell the user and offer to accept a freeform lesson from them.
3. Check global scope for duplicates
Search both stores for an existing entry covering the same topic. Track which store the duplicate came from:
-
Search the knowledge database (if available):
node ${INSTALL_ROOT}/.claude/hooks/knowledge-db.js search "<topic keywords>" 2>/dev/nullIf a match is found here, set
duplicate_source = "knowledge.db". -
Read
${INSTALL_ROOT}/.claude/CLAUDE.mdand scan for any existing entry covering the same topic. If a match is found here, setduplicate_source = "CLAUDE.md".
If a near-duplicate is found in either store, tell the user (noting where it was found):
A similar lesson already exists in global scope (<duplicate_source>):
"<existing text>"
Options:
s - skip (keep existing)
u - update (replace existing with new lesson)
a - add anyway (keep both)
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.
- 8d ago First seen · 115 lines · 53 tokens per session scan A fb24573031ba
promote is a skill published in the GitHub repository john-wilmes/claude-agentic-coding-playbook (4 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 915 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
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
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
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-git-memory
Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.