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/rbah31/claude-code-workflow/wiki-reviewnpx skills add rbah31/claude-code-workflow --skill wiki-reviewgit clone --depth 1 https://github.com/rbah31/claude-code-workflowWrote 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/rbah31/claude-code-workflow/wiki-review)<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/wiki-review"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/wiki-review.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 | $0.00108 | $0.01039 |
| Opus 5 | $0.00054 | $0.00519 |
| Sonnet 5 | $0.00022 | $0.00208 |
| Haiku 4.5 | $0.00011 | $0.00104 |
Grade A, and why
wiki-review 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 6d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki review — merge proposals into the wiki
The wiki/ directory is the project's source of truth and is gate-locked
by the block_wiki_write.py PreToolUse hook. This skill is the single
legitimate path that bypasses the gate.
Prerequisites
- A
wiki/directory exists at the project root (the hook only fires on writes targetingwiki/**). - One or more proposal files under
briefs/wiki-proposals/*.mdwith frontmatter declaringtarget:(the wiki path they should land at).
If no proposals exist, exit with a one-line message: "No proposals in
briefs/wiki-proposals/. Nothing to review."
Workflow
Step 1 — Inventory
List briefs/wiki-proposals/*.md. Skip:
README.md- Files starting with
EXAMPLE- - Subdirectories (e.g.
archive/)
Report the count to the human: "N proposals to review."
Step 2 — Walk each proposal
For each proposal, in chronological order (filename starts with date):
- Read the proposal. Extract
target:from frontmatter (the wiki path it should land at) and the body. - Show a one-paragraph summary to the human (target path + 2-3 sentence gist of the proposal).
- Ask: merge as-is / rewrite / discard / defer ?
- Branch on the answer (Step 3, 4, 5, or 6).
Step 3 — Merge as-is
- Create the sentinel:
touch .claude/.wiki-review-active(an empty file is enough — the hook checks existence, not content). - Write the proposal body to the target wiki path declared in the frontmatter. Create parent directories if needed.
- Delete the proposal file from
briefs/wiki-proposals/. - Remove the sentinel:
rm .claude/.wiki-review-active.
If the write fails or the user interrupts mid-merge: still remove the sentinel before exiting. A leftover sentinel disables the gate for the next session.
Step 4 — Rewrite
Ask the human for the changes (which sections, what tone, what to cut). Apply them to the proposal body in memory. Then proceed with Step 3 (merge the rewritten version, delete the original proposal).
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.
- 6d ago First seen · 112 lines · 108 tokens per session scan A 718e3ef1228d
wiki-review is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,039 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 2026-08-31.
Other skills, from other repositories
unified-memory
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. Use when a session is approaching a context limit and a task phase is a natural place to compact.
agents-md-improver
Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or…
moai-foundation-context
Manages context window optimization, session state persistence, and token budget allocation for multi-agent workflows. Use for token budget management, context limits, or session handoff across agents.
agents-md-revise
Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit. Use when the user says "revise the rules", "update AGENTS.md / CLAUDE.md with what we just learned", "save this to project memory", "remember this for next time", or at the end…
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…