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 kununu/agent-bridge --skill bridge-reviewgit clone --depth 1 https://github.com/kununu/agent-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/kununu/agent-bridge/bridge-review)<a href="https://agentmods.dev/skills/kununu/agent-bridge/bridge-review"><img src="https://agentmods.dev/badge/skills/kununu/agent-bridge/bridge-review/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/kununu/agent-bridge/bridge-review"><img src="https://agentmods.dev/badge/skills/kununu/agent-bridge/bridge-review.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 | $0.00044 | $0.00593 |
| Opus 5.5 | $0.00018 | $0.00237 |
| Sonnet 5.5 | $0.00009 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
bridge-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 15d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bridge-review
A peer agent reviews the work, you decide what is real.
1. Pick the peer
The invocation names the peer: /bridge-review gemini, /bridge-review codex,
/bridge-review claude. With no peer named, never make assumptions, ask the human which one to use.
If this skill has a references/<peer>.md, read it. It records that peer's quirks. No file
means no quirks. gemini is bridge peer agy.
2. Send the review
Call the Skill tool with "agent-bridge" and delegate to the peer.
The brief carries the context the peer cannot see:
- Goal. What this change is for, so it can judge whether the code is the simplest way there.
- Gotchas. The things you discovered during implementation that the peer should be aware of. If there are none, just skip this section.
- Scope. Which files or which diff to review, by path or commit range.
- Standards, both layers: the coding-standards skill, and this repo's own conventions in AGENTS.md, CLAUDE.md, local project skills and any standards docs. Where the two disagree, the repo wins.
- Ask: code quality, adherence to both layers of standards, best practices, the simplest code that reaches the goal, efficiency & performance.
- The output shape: for each finding,
file:line, what breaks, and why it matters. Ranked, worst first. - Review only. It reports findings and leaves the working tree as it found it.
3. Verify every finding
Never act on a finding you have not checked against the code, or verified some other way (e.g. look up current documentation). How you check depends on the finding: read the file, run the test, try the input, write and run temp script. A finding is real once you can name what breaks or what will break. If you cannot name it, it is noise.
4. Fix or ask
Fix it yourself when the change is small and obvious:
- Cleanups that leave behavior identical: a standards violation, a code smell, the same logic written more simply.
- A real bug whose fix is clear and local, however serious it is.
What ships with it
1 file 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.
- 15d ago Changed 57f83a46f2a8
- 27d ago Changed bd62dc421ec8
- 2mo ago First seen · 55 lines · 44 tokens per session scan A 1214eb4f6041
bridge-review is a skill published in the GitHub repository kununu/agent-bridge (18 stars, last pushed 16d ago), licensed MIT. It adds 44 tokens to every session and 593 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…