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/swimmwatch/cloakbrowser-mcp/spec-driven-developmentnpx skills add swimmwatch/cloakbrowser-mcp --skill spec-driven-developmentgit clone --depth 1 https://github.com/swimmwatch/cloakbrowser-mcpWrote 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/swimmwatch/cloakbrowser-mcp/spec-driven-development)<a href="https://agentmods.dev/skills/swimmwatch/cloakbrowser-mcp/spec-driven-development"><img src="https://agentmods.dev/badge/skills/swimmwatch/cloakbrowser-mcp/spec-driven-development.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 | $0.00089 | $0.00786 |
| Opus 5 | $0.00044 | $0.00393 |
| Sonnet 5 | $0.00018 | $0.00157 |
| Haiku 4.5 | $0.00009 | $0.00079 |
Grade A, and why
spec-driven-development 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 5d 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.
What it actually says
Spec-Driven Development
Write the smallest complete contract that prevents implementation from inventing behavior. Keep the entire workflow specification-only.
- Read
AGENTS.md,.agents/references/specification-interview.md, the closest relevant public docs, affected code/tests/configuration, package and workflow contracts, and existing specification bundle. Use CodeGraph before broad source search when indexed. - Select a stable slug and create
docs/specs/<slug>/decisions.yamlbefore the first material question. Keepspec.mdseparate from interview state. - Establish repository-observable facts first. Record evidence-backed facts
as
observed, explicit request decisions asanswered, reversible defaults as visibleassumedentries, and irrelevant categories asnot_applicable. - Inspect the Prompt MCP schemas. Start or reopen the persistent workspace
interview
spec:<slug>. Checkpoint pending ledger entries before displaying them, use stable semantic IDs, and save each returned status and committed result immediately. - Use
ask_user_batchfor one to five related decisions orask_userfor one focused decision. Choosesingle,multiple, ortextfrom answer semantics. Do not substitute plain-chat multiple choice while Prompt MCP is callable. - Cover outcome and stakeholders; scope and non-goals; normal and alternate flows; invalid input and failures; interfaces and data; architecture and dependencies; security and privacy; configuration and operations; compatibility and migration; and objective automated/manual acceptance.
- Derive follow-ups for implications, limits, exceptions, concurrency, cleanup, rollback, contradictions, and external effects. A cancelled, timed-out, unavailable, invalid, conflicting, failed, paused, or unresolved result is not an answer.
- After interruption or compaction, reload the ledger, inspect the persistent interview, reconcile revisions, and resume unresolved questions only. Preserve superseded answers as new revisions; never overwrite or repeat a committed decision unnecessarily.
- Run the reference's gap analysis from user, operator, implementer, tester, security reviewer, and maintainer perspectives. A deferred material decision is a blocker, not an implementation assumption.
- Normalize active decisions into numbered requirements, defaults, constraints, non-goals, compatibility duties, and objective acceptance criteria. Map every active ledger item to requirement IDs.
- Write
docs/specs/<slug>/spec.mdwithStatus: Draft. Exclude raw transcript, model reasoning, task sequence, estimates, and implementation packets. - After the complete draft is inspectable, checkpoint
approval.specand ask a separate Prompt MCPsinglequestion withapprove,request-changes, andleave-draft. - Set
Status: Approvedonly after an explicit committedapproveanswer. Custom text requests changes and cannot implicitly approve. - Report the specification, ledger, unresolved blockers, and evidence, then
stop. Recommend
/planonly as a separate next invocation.
This skill is the single authoritative /spec route. Never begin planning,
implementation, commit, push, PR, release, or publication automatically, and
never request or persist secrets.
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.
- 5d ago First seen · 61 lines · 89 tokens per session scan A 8a13fb3c53a1
spec-driven-development is a skill published in the GitHub repository swimmwatch/cloakbrowser-mcp (56 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 786 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
browser-search
Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser). Use whenever you need to do web research.
chrome-orchestrator
Teach agents how to orchestrate Arthur and Gloria headless Chrome environments dynamically via the Python SDK and CLI.
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.