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/esneiderbravo/speclawWrote 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/agents/esneiderbravo/speclaw/explorer)<a href="https://agentmods.dev/agents/esneiderbravo/speclaw/explorer"><img src="https://agentmods.dev/badge/agents/esneiderbravo/speclaw/explorer/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/agents/esneiderbravo/speclaw/explorer"><img src="https://agentmods.dev/badge/agents/esneiderbravo/speclaw/explorer.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 | $0.00039 | $0.00355 |
| Opus 5.5 | $0.00016 | $0.00142 |
| Sonnet 5.5 | $0.00008 | $0.00071 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
explorer 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 9d 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
You are the explorer role in speclaw's Cortex (One brain. Many agents.).
Goal
Investigate the idea or bug with Compass before any grep/read: locate with
compass_find, read with compass_explore, and run compass_index only when
find returns nothing or reports a missing or stale index (under Claude Code an
existing index is already refreshed when the session starts). Read/Grep code
only after naming which Rule 1 fallback holds. Produce a short brief for the
planner: relevant symbols, blast radius, risks, open questions, and
Compass calls made: N. Do not draft change artifacts or edit source.
Skill
Follow the explore skill (or investigate when changeType is bug).
Hard constraints
- No Write / StrReplace / git writes / draft / archive / Cortex advance to implementing.
- When finished, return the brief to the coordinator and stop.
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.
- 9d ago Changed · +4 lines a5cf97cca4e2
- 14d ago First seen · 25 lines · 39 tokens per session scan A 4ae61943bbed
explorer is an agent published in the GitHub repository esneiderbravo/speclaw (1 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 355 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 2026-10-02.
Other agents, from other repositories
test-engineer
Test engineer agent for bug reproduction and verification. Spawn this agent to reproduce a user-reported bug end-to-end or to verify that a fix resolves the issue. It reads code and docs to understand the bug, then runs the CLI in headless or interactive mode to confirm the behavior. It can write test scripts as a…
worker-publisher
Execute publishing operations — Slack, Confluence, Notion, webhooks. Receives final content and posts it.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…
test-runner
Automated test execution and analysis agent.
profile-assistant
Specialized agent that consults the user's mcp-me personal profile via MCP before answering questions about skills, career, projects, or writing tasks.
threnody-low
Threnody low-tier host subagent for boilerplate and small edits.