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 Sixz-AI/repo-knowledge --skill rk-updategit clone --depth 1 https://github.com/Sixz-AI/repo-knowledgeWrote 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/sixz-ai/repo-knowledge/rk-update)<a href="https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-update"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-update/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/sixz-ai/repo-knowledge/rk-update"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-update.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 | $0.00077 | $0.00919 |
| Opus 5 | $0.00039 | $0.00460 |
| Sonnet 5 | $0.00015 | $0.00184 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
rk-update 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 10d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RK Update — Incremental Knowledge Base Update
Input
- Project name (must already exist in registry)
Step 1: Resolve home directory (cross-platform)
python3 -c "import os; print(os.path.expanduser('~'))"
Store as {HOME}. Base path: {HOME}/.repo-knowledge.
Step 2: Auto-pull from remote (if configured)
Check if {HOME}/.repo-knowledge/_remote.md exists.
If it exists: run the full merge flow from rk-pull (Steps 3–7) before doing anything else.
This ensures local knowledge is up to date with all other machines before we add new changes.
Step 3: Check project type
Read {HOME}/.repo-knowledge/<project-name>/_meta.md.
If type: personal or git_url: none is found:
- Tell user: "
<project-name>is a personal knowledge base — use/repo-knowledge:rk-memoto add or update entries." - Stop here.
Step 4: Ensure source repo exists
Check if {HOME}/.repo-knowledge/_repos/<project-name>/ exists.
If it does NOT exist:
- Read
{HOME}/.repo-knowledge/<project-name>/_meta.mdto getgit_url - Clone the source repo:
git clone <git_url> {HOME}/.repo-knowledge/_repos/<project-name> - Continue — the repo is now available locally.
Step 4: Read project metadata
Read {HOME}/.repo-knowledge/<project-name>/_meta.md.
Extract: last_commit hash.
Step 5: Pull latest source code
git -C {HOME}/.repo-knowledge/_repos/<project-name> pull
Step 6: Find changed files since last sync
git -C {HOME}/.repo-knowledge/_repos/<project-name> diff --name-only <last_commit>..HEAD
If no files changed: tell user "Already up to date." Skip to Step 8 (auto-push still runs if remote is configured).
Step 7: Process each changed file
Launch an Agent with this prompt:
You are a Knowledge Base Update Agent.
Codebase path: "{HOME}/.repo-knowledge/_repos/{project-name}/"
Cache path: "{HOME}/.repo-knowledge/{project-name}/"
Changed files:
{list of changed files from git diff}
## For Each Changed File:
### If file was MODIFIED:
1. Read the new version of the file
2. Find all functions/classes in it
3. Check if docs already exist for them in the cache
4. Regenerate the docs with updated code
5. Update the cached .md files
### If file was ADDED:
1. Read the file
2. Generate docs for each function/class (same format as rk-create)
3. Save to cache
4. Append to _index.md
### If file was DELETED:
1. Find cached docs that reference this file (check `source:` in frontmatter)
2. Delete those cached .md files
3. Remove entries from _index.md
## After processing all files:
1. Update _meta.md with new last_commit and last_update date
2. Update total_docs count
3. Update _registry.md row for this project
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.
- 10d ago First seen · 116 lines · 77 tokens per session scan A 8dbfc08b3a87
rk-update is a skill published in the GitHub repository Sixz-AI/repo-knowledge (2 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 919 once invoked, about $0.0004 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
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
session-handoff
Create consistent session handoff documents for context transfer between sessions. Use when closing a session, reaching 75% token consumption, or when user requests handoff. Ensures proper YAML headers for metrics collection, LF line endings, and complete documentation of progress, decisions, and next steps.
recall
Answer "why" and "when" questions about a project's decisions — the intent behind a past choice, when it was made, what was tried before and rejected. Use when asked why something was decided, what the rationale was, or before reversing or redoing earlier work. For why the code mechanically behaves a certain way use…
session-handoff-number-collision-with-unmerged-sibling
Detect and recover from a session-number collision when running session-handoff and a parallel/sibling session has authored a same-numbered handoff doc that hasn't merged into main yet. Use when: (1) you're in session-handoff Phase 1 about to write docs/handoffs/sessionNNNhandoff.md, (2) ls docs/handoffs/ shows the…
writing-github-docs
Write the repository's public face — README.md, CONTRIBUTING.md, and the GitHub community health files (SECURITY, CODEOFCONDUCT, LICENSE, issue and pull request templates). Use this when creating or rewriting any of those, when deciding whether a sentence belongs in the README or in CONTRIBUTING, when GitHub's…
brain-hydrate
Use when users want to bootstrap the brain with existing project knowledge -- reading ADRs, feature specs, UX docs, commit history, and error patterns to seed institutional memory on a project that already has artifacts on disk. Also use for incremental re-hydration after significant work outside the pipeline.…