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 bks-lab/open-bridge --skill knowledge-repo-initgit clone --depth 1 https://github.com/bks-lab/open-bridgeWrote 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/bks-lab/open-bridge/knowledge-repo-init)<a href="https://agentmods.dev/skills/bks-lab/open-bridge/knowledge-repo-init"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/knowledge-repo-init.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 33 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 200 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00124 | $0.02265 |
| Opus 5 | $0.00062 | $0.01132 |
| Sonnet 5 | $0.00025 | $0.00453 |
| Haiku 4.5 | $0.00012 | $0.00227 |
Grade A, and why
knowledge-repo-init 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Repo Init — Guided Wizard
Sets up an optional knowledge/documentation repo paired with this
Bridge instance. Bridge works without one — this skill is for users who
have outgrown a flat work/log.md and want a durable place for
protocols, decisions, and customer documentation.
Pattern overview: docs/knowledge-repo-pattern.md
— read it first if you're unsure whether you want this. The wizard
itself does not repeat the pattern explanation; it executes it.
Before you start
The wizard performs filesystem writes (creates folders, copies
templates) and edits Bridge configs (ecosystem.yaml,
workflow/contexts/<slug>.yaml). It does not touch your knowledge
repo's Git history without confirmation. Every destructive or
externally-visible step is gated by an explicit [y] prompt.
Inputs the wizard collects
| Phase | Question | Default |
|---|---|---|
| 0 | What's the state? new repo / existing repo / both | — |
| 1 | Slug + display name + (optional) org | — |
| 2 | Path on disk + remote URL (if any) | local-only OK |
| 3 | Top-level areas (customers/internal/leads/partners/projects) | internal/ |
| 4 | Dual-doku contract for any area? | no |
| 5 | Bridge integration: register in ecosystem.yaml? |
yes |
| 6 | Scaffold a starter project folder? | optional |
| 7 | Commit + push? | confirm |
Use AskUserQuestion for branching choices. Bundle related fields into the same prompt when they're not branching (slug + display name + org together, areas as multi-select).
Phase 0 — State detection
Ask:
Do you already have a knowledge repo, or are we creating one fresh? [1] Fresh — create a new directory + (optional) GitHub repo [2] Existing — wire up a repo that already lives somewhere on disk [3] Both — point at an existing folder AND scaffold a new project inside it
For [1] and [3], the wizard will create folders and write files. For [2], the wizard reads the existing layout and only proposes template additions — it never overwrites existing files.
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 · 245 lines · 124 tokens per session scan A 3a8e5676b3c7
knowledge-repo-init is a skill published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed today), licensed MIT. It adds 124 tokens to every session and 2,265 once invoked, about $0.0006 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
state-management
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with structured fields for current task, completed phases, blockers, decisions, and quick tasks.
mem0-integration
Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.
context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
persistent-memory
Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.
context-management
Project context loading, isolation, and persistent state management across CCPM sessions.
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…