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 spec-kickoffgit 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/spec-kickoff)<a href="https://agentmods.dev/skills/bks-lab/open-bridge/spec-kickoff"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/spec-kickoff/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/bks-lab/open-bridge/spec-kickoff"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/spec-kickoff.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 | $0.02088 |
| Opus 5.5 | $0.00036 | $0.00835 |
| Sonnet 5.5 | $0.00018 | $0.00418 |
| Haiku 4.5 | $0.00009 | $0.00209 |
Grade A, and why
spec-kickoff 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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Kickoff
A phased, checkpointed kickoff for starting a new build the right way — Andrej
Karpathy's three layers (spec → verifier → environment), expressed through Claude
Code's own primitives. You produce one self-contained SPEC.md that ends in an
end-to-end verification step, then hand off to the build.
This is not a new framework. It is spec-kit's discipline + Kiro's EARS/gates,
expressed through Anthropic's native "interview → SPEC.md → verify-loop" pattern,
wired into the environment the user already has. Conceptual depth, the verified
Karpathy sources, and the EARS / ladder / gate cheat-sheets live in
references/method.md. The artifact you fill is
assets/SPEC.md. A one-page visual explainer for humans (open in a
browser) ships at assets/spec-kickoff-explainer.html.
Talk to the user in their conversation language. Keep the interview sharp and short — a handful of load-bearing questions, not a survey. This skill is opt-in: when invoked the structure is wanted, but never let it become a ceremony tax.
Phase 0 — Frame & skip-check (≈30 seconds)
-
Skip-gate first. If any of these holds, say so and do NOT run the kickoff:
- you could describe the whole change in one sentence (Anthropic: skip the plan);
- it's a quick fix (≲10 min, <3 files);
- you're mid-build, not starting something new.
→ Point at the normal build flow. The method is for substantial new builds.
-
Autonomy level (Karpathy's autonomy slider): tight / medium / wide — how much leash the build gets. Default tight; widen only as the verifier earns trust.
-
Where the spec lives. Copy
assets/SPEC.mdto the task's home. On a Bridge instance that'swork/tasks/<slug>/SPEC.md— fold it into the reflex-pause / task, don't create a parallel artifact.
Phase 1 — SPEC (Layer 1: the human owns the goal)
Run an interview — use AskUserQuestion for branching decisions. Cover, in order:
What ships with it
3 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.
- 1mo ago Changed · -10 lines · -202 tokens per session 5fb4ccb8009a
- 1mo ago First seen · 150 lines · 292 tokens per session scan A 8f5248c4d049
spec-kickoff is a skill published in the GitHub repository bks-lab/open-bridge (13 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 2,088 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
scenario-design
Draft real-life test SCENARIOS (not smoke tests) from a change/feature spec. Derives edge-case, performance, frontend-quirk and error-handling scenarios with ISTQB techniques, routes each to a test level, and writes test-plan.md, emitting clarification questions on a spec gap. Use on "design test scenarios", "what…
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
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…