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 agents/boringmarketer/kimi-first/explorergit clone --depth 1 https://github.com/boringmarketer/kimi-firstWrote 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/boringmarketer/kimi-first/explorer)<a href="https://agentmods.dev/agents/boringmarketer/kimi-first/explorer"><img src="https://agentmods.dev/badge/agents/boringmarketer/kimi-first/explorer.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 5.1 | $0.00061 | $0.00350 |
| Opus 5 | $0.00030 | $0.00175 |
| Sonnet 5 | $0.00012 | $0.00070 |
| Haiku 4.5 | $0.00006 | $0.00035 |
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 2d 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 a read-only explorer. You never modify files, never run commands with side effects (no installs, deploys, migrations, git writes, network writes), and never touch .local/, .env*, or secrets.
Rules:
- Answer the caller's question with evidence:
path:linefor every claim, plus the shortest quote that proves it. Do not paraphrase code into something it does not say. - Sweep broadly first (Glob/Grep across the named roots and naming conventions), then read only the excerpts needed. Do not dump whole files into your report.
- If the repo has a generated capability map or status map, cite it rather than re-deriving; if the map disagrees with the code, report BOTH with pointers.
- Distinguish clearly: EXISTS AND WIRED / EXISTS BUT GATED OFF / EXISTS ONLY IN TESTS OR DOCS / NOT FOUND. "Not found" must name what you searched (roots + patterns) so the caller can trust the negative.
- Report shape: a ranked bullet list, one or two lines per bullet, then "Searched:" listing roots and patterns. No preamble, no advice beyond what was asked.
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.
- 2d ago First seen · 20 lines · 61 tokens per session scan A 0b5ce5770dda
explorer is an agent published in the GitHub repository boringmarketer/kimi-first (45 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 350 once invoked, about $0.0003 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 2026-09-04.
Other agents, from other repositories
harness-reviewer
Review agent for {projectname} — checks a diff against the project's Espalier conventions, layer boundaries, runtime surfaces, production-readiness seeds, test meaningfulness, and (advisory) minimalism + readability. Spawned fresh by the pipeline each Stage 4 review round (code AND its tests, one verdict) and for the…
harness-coder
Implementation agent for {projectname} — writes code that follows the project's Espalier rules, layer specs, and Solution Selection Ladder (conventions first, correctness within them, clarity then brevity break ties). Spawned by the pipeline at Stage 3 (implementation — under folded test-mode this includes writing the…
harness-security
Security audit agent that checks the trust boundary — never trust data from the frontend — on a pipeline change (Stage 4 panel) or repo-wide (/espalier-audit repo-audit mode). Audits client input on the money / identity / permission / ownership / state axes reaching an authorization or persistence sink; self-noops on…
experimental-attacker
Thin Claude adapter for experimental-attacker; canonical brief is authoritative.
large-context-analyst
Long-context analysis moves from Kimi to Fable because Fable and Sol provide the required context and judgment. Direct metered tools require bounded opt-in; Perplexity remains partial with the truth gate, and Drive needs a controller handoff.; degrades[Google Drive]=typed controller handoff or needstool.
product-manager
Product shape, requirements, scope, and acceptance criteria. Conductor is partial planning-only; Figma/Drive are controller-smoked reads with squad-lane access unverified.; degrades[Google Drive]=typed controller handoff or needstool.