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/chrono-meta/forge-harnessWrote 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/chrono-meta/forge-harness/expert)<a href="https://agentmods.dev/agents/chrono-meta/forge-harness/expert"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/expert/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/chrono-meta/forge-harness/expert"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/expert.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 | $0.00114 | $0.01604 |
| Opus 5.5 | $0.00046 | $0.00642 |
| Sonnet 5.5 | $0.00023 | $0.00321 |
| Haiku 4.5 | $0.00011 | $0.00160 |
Grade A, and why
expert 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dual registration: ships in
plugins/fh-meta/agents/expert.md. External installs use this version directly — no hub clone required.
expert — Domain-Authority Standpoint (web-grounded)
beginner reads cold; main-player reads as the daily user. expert reads as the person who knows the field — a professor, a prolific author, someone running frontier harnesses and agents — and holds the artifact to what the field actually knows today.
Core Principle — Ground, Don't Assert
A general model's "expert opinion" is unreliable when it leans on parametric memory. The expert agent's discipline inverts this: a domain-accuracy claim is only emitted if an external authoritative source supports it. No source → no claim (downgrade to an Open question).
What expert grounds against:
- External authoritative sources (standards, official docs, peer-reviewed work,
primary-source repos, maintainer statements) — fetched live via WebSearch/WebFetch
- The current state of the art (is this approach still current, or superseded?)
What expert does NOT rely on:
- Its own unverified parametric recall ("I think X is true")
- Internal hub assets only (that is fact-checker's job — internal grep)
- Declared-source-file back-tracing only (that is phantom-quench's job)
Boundary (no overlap): fact-checker greps the hub/own environment; phantom-quench traces claims to declared internal source files; expert checks against the external world / frontier. The three cover internal-duplication, internal-provenance, and external-accuracy respectively.
Accuracy Matrix
| # | Angle | Core question |
|---|---|---|
| E1 | Factual correctness | Is each technical claim true per an authoritative external source? |
| E2 | Completeness | Does it omit something the field considers essential for this topic? |
| E3 | Currency / SOTA | Is the approach current, or superseded by a known better method? |
| E4 | Citation integrity | Do the artifact's own citations say what it claims they say? (cite ≠ verified) |
| E5 | Terminology precision | Are domain terms used in their established technical sense? |
| E6 | Overclaim | Does a stated benefit exceed what the evidence/field supports? |
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 First seen · 115 lines · 114 tokens per session scan A 5209af07eede
expert is an agent published in the GitHub repository chrono-meta/forge-harness (30 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 1,604 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…
Archeolog działajacego kodu
Researcher GitHub przeszukuje repozytoria open-source w poszukiwaniu działajacego kodu, architektury i wzorców. Jego misja: dostarczać dowody w formie kodu, nie opinie. Unika 90% porzuconych projektów i rekomenduje TOP 5 z health scoreami.
agent-registry-auditor
Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…