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.
git clone --depth 1 https://github.com/chan4lk/specclawWrote 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/plugins/chan4lk/specclaw/specclaw-extras)<a href="https://agentmods.dev/plugins/chan4lk/specclaw/specclaw-extras"><img src="https://agentmods.dev/badge/plugins/chan4lk/specclaw/specclaw-extras/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/plugins/chan4lk/specclaw/specclaw-extras"><img src="https://agentmods.dev/badge/plugins/chan4lk/specclaw/specclaw-extras.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
specclaw-extras 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 today.
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
{
"name": "specclaw-extras",
"version": "0.8.2",
"description": "Optional specclaw skills: auto, loop, learn, patterns, context, author-spec, debug, renumber and the review panel.",
"author": {
"name": "Chandima Ranaweera",
"email": "[email protected]"
},
"homepage": "https://github.com/chan4lk/specclaw",
"repository": "https://github.com/chan4lk/specclaw",
"license": "MIT",
"keywords": [
"spec-driven",
"automation",
"review"
]
}
What it installs
The manifest is a name and a version. 8 skills, 7 agents travel with it, and installing the plugin installs all of them — 257 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill loop A 15 tokens
- Skill debug A 24 tokens
- Skill learn A 17 tokens
- Skill patterns A 15 tokens
- Skill context A 20 tokens
- Skill renumber A 16 tokens
- Skill author-spec A 19 tokens
- Skill auto A 16 tokens
- Agent party-architect A 14 tokens
- Agent party-classifier A 17 tokens
- Agent party-security A 16 tokens
- Agent party-visionary A 18 tokens
- Agent party-ba A 15 tokens
- Agent party-po A 16 tokens
- Agent spec-author A 19 tokens
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.
- today Changed 3a6be81587bb
- 4d ago First seen · 18 lines scan A f9c9c246d928
specclaw-extras is a plugin published in the GitHub repository chan4lk/specclaw (13 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-13.
Other plugins, from other repositories
craft
A Claude Code plugin that acts as an intelligent harness for your development workflow: your codebase is read-only by default, every change passes through a Write Gate as planned and approved work, and craft tracks your project's history, design tokens, and decisions locally so Claude learns your taste and…
aspark
An agile AI product team for Claude Code — Specify, Plan, Act, Review, Keep. A Product Owner, Designer, Engineering Manager, Reviewer, QA Tester and Release Manager work your feature through a gated delivery loop.
loki-mode
Autonomous spec-to-product build system with a built-in trust layer (RARV-C closure loop, 8 quality gates, completion council). Ships Loki's spec-hardening, drift-detection, and deterministic PR verification commands plus the Loki MCP server.
claude-skills
Skills and agents that add lifecycle gates around planning and building with Claude Code, with each kind of job running on its own model and effort: ground a plan in reality, verify a finished diff with fresh eyes, audit injected context, set up per-repo permissions so you can run auto mode with confidence, and turn a.
fable-workflow
Fable-style agentic working method for any model — surface the unknowns before building on vague specs or unfamiliar code (blind-spot pass, interview, variants, log assumptions, stay in the loop).
goalify
Hand Claude a huge task. Come back to proof it's done, not a promise that it is.