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/bks-lab/open-bridge/bridge-learnnpx skills add bks-lab/open-bridge --skill bridge-learngit 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/bridge-learn)<a href="https://agentmods.dev/skills/bks-lab/open-bridge/bridge-learn"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/bridge-learn.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 | $0.00198 | $0.03319 |
| Opus 5 | $0.00099 | $0.01659 |
| Sonnet 5 | $0.00040 | $0.00664 |
| Haiku 4.5 | $0.00020 | $0.00332 |
Grade A, and why
bridge-learn 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 4d 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 — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bridge Learn — Review Surface for Improvement Proposals
/bridge-learn is the Layer-3 edge of the Bridge Learning-Loop architecture
(see work/_learning/README.md). It consumes proposals written by
task-close-postmortem (Phase 1) or /bridge-audit recurring findings
(Phase 3) and walks the user through accept/reject decisions.
Never auto-apply. Every accepted proposal is materialized through a git
commit on user/<name>, audit-trail.md records it, git revert is always
the rollback path.
When to use
| Trigger | Mode |
|---|---|
User says /bridge-learn / "review proposals" / "learn review" |
Interactive — full walk-through |
| /briefing skill invokes (Fridays, when pending ≥ threshold) | Summary — count + 1-line list, no walk |
User says /bridge-learn list |
List-only — no actions, just an overview |
User says /bridge-learn trends |
Trends — recurring + sleeping skills, no proposals |
User says /bridge-learn <proposal-id> |
Single — go directly to that proposal |
Inputs
work/_learning/proposals/*.md— all pending proposalswork/_learning/audit-trail.md— lifecycle log (for statistics)work/_learning/audit-history/— Phase 3, for trends sectionbridge-config.yaml.learning— thresholds (auto_surface_threshold etc.)- (Optional)
work/_learning/skill-usage.jsonl— Phase 4, for "sleeping skills"
Interactive walk-through
Header
═══ Bridge Learning Review — 2026-05-13 ═══
📋 Pending Proposals (N)
P0 <id-1> (<source-type>)
P1 <id-2> (<source-type>)
P2 <id-3> (<source-type>)
...
📈 Trends (last 30d) [if audit-history populated]
Audit findings: P0=0 P1=12→8 P2=23→27 P3=5
Skills inactive: <N> of <total> [if skill-usage populated]
Task estimate-vs-actual: median 1.4x (vs 1.2x last month)
🔁 Recurring patterns (≥3 occurrences)
- <pattern-1> [→ proposal/audit-recurring exists]
- <pattern-2> [new — consider Standing-Order]
→ Review proposals one by one? [y/N]
→ Or: trends / list / quit
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 319 lines · 198 tokens per session scan A 8543f2373a38
bridge-learn is a skill published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed 5d ago), licensed MIT. It adds 198 tokens to every session and 3,319 once invoked, about $0.0010 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
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
with-frontmatter
Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.
minimal
Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.
beevibe-team-mesh-negotiation
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
beevibe-verify-pr
CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…
beevibe-use-repo
You are the child agent inside a fresh Docker sandbox. Borrow the given GitHub repo, produce a real artifact for the goal, and export it. Do not review the repo. The proof is that it works.