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-pullgit 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-pull)<a href="https://agentmods.dev/skills/sixz-ai/repo-knowledge/rk-pull"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-pull/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-pull"><img src="https://agentmods.dev/badge/skills/sixz-ai/repo-knowledge/rk-pull.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 | $0.00090 | $0.00940 |
| Opus 5 | $0.00045 | $0.00470 |
| Sonnet 5 | $0.00018 | $0.00188 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
rk-pull 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RK Pull — Pull Remote Knowledge Base to Local
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: Check remote is configured
Read {HOME}/.repo-knowledge/_remote.md.
If not found: tell user to run /repo-knowledge:rk-remote-init <git-url> first. Stop.
Step 3: Fetch remote
git -C {HOME}/.repo-knowledge fetch origin main
Step 4: Check if remote has new commits
git -C {HOME}/.repo-knowledge rev-list HEAD..origin/main --count
If count = 0: tell user "Already up to date." Stop.
Step 5: Identify changed files
git -C {HOME}/.repo-knowledge diff HEAD origin/main --name-only
Step 6: Agent merge for each changed file
Process each file from the diff. Use git -C {HOME}/.repo-knowledge show origin/main:<relative-path> to read the remote version.
_registry.md
- Read local
{HOME}/.repo-knowledge/_registry.md - Read remote:
git -C {HOME}/.repo-knowledge show origin/main:_registry.md - Union of all data rows, deduplicate by project name, keep the row with the most recent
Last Updatedate for duplicates - Write merged result with Write tool
<project>/_index.md
- Read local version
- Read remote:
git -C {HOME}/.repo-knowledge show origin/main:<project>/_index.md - Parse entries by doc path
- Merge:
- Same doc path in both: union aliases, deduplicate, keep first 10 (remote aliases go first here — remote is the newer authoritative source in a pull)
- Only in remote: append to local (new knowledge from other machines)
- Only in local: keep as-is
- Write merged
_index.md
<project>/docs/*.md
- Read local file frontmatter (
cached:field) - Read remote:
git -C {HOME}/.repo-knowledge show origin/main:<path> - Keep whichever has the newer
cached:date - If remote is newer: overwrite local with Write tool
<project>/_meta.md
- Read both versions
- Merge:
last_update= newer date,total_docs= higher number,git_url= either,last_commit= from side with newerlast_update - Write merged result
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 · 94 lines · 90 tokens per session scan A 2adc7cd3aa18
rk-pull is a skill published in the GitHub repository Sixz-AI/repo-knowledge (2 stars, last pushed 4mo ago), licensed MIT. It adds 90 tokens to every session and 940 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
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.
memory
Memory discipline. Load when the agent keeps persistent memory across sessions - CLAUDE.md, AGENTS.md, auto-memory, memory banks, or any notes file the next session will read. Covers writing selectively, never recording what the repo already knows, structuring memory as index plus topics, stamping claims that can go…
code-to-docs-digest
Load existing code-to-docs vault context into the conversation before coding. Read-only — never writes files. Provides architecture overview, module summaries, known issues, and session history. Use when starting a coding session, loading doc context, or catching up on a documented codebase.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.