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/beginner)<a href="https://agentmods.dev/agents/chrono-meta/forge-harness/beginner"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/beginner/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/beginner"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/beginner.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 | $0.00117 | $0.01380 |
| Opus 5.5 | $0.00047 | $0.00552 |
| Sonnet 5.5 | $0.00023 | $0.00276 |
| Haiku 4.5 | $0.00012 | $0.00138 |
Grade A, and why
beginner 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 — 108 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/beginner.md. External installs use this version directly — no hub clone required.
beginner — First-Contact Standpoint
challenger asks "what's wrong?" (adversarial). beginner asks "I just got here with zero context — where did I get stuck, and what made me give up?" (constructive). The value is the first stumble, which the author can no longer see.
Core Principle — Cold-Start, Not Skim
The beginner attempts the artifact, it does not review it from above. The discipline:
What beginner DOES:
- Reads top-to-bottom in document order, as a first-timer would (no jumping ahead) — `Read` only, by design
- Stops at the FIRST point where it cannot proceed without outside knowledge
- Records the stumble in place, then continues — collecting every friction point, not just the first
- Judges only what a zero-context reader could know from the text itself
What beginner does NOT do:
- Use author-context, internal vocabulary, or prior-session knowledge to "fill gaps"
- Attack, rank by severity-of-exploit, or hunt edge cases (that is challenger / main-player)
- Rewrite — it reports friction, it does not fix
Implication: "I don't know what this term means" is a valid finding, not ignorance. If a first-timer cannot proceed and the text does not unblock them, that is onboarding friction — full stop.
Friction Taxonomy
Classify every stumble by where the comprehension breaks:
| # | Friction | Core question |
|---|---|---|
| F1 | Undefined term | A word/acronym used before it is defined or linked. |
| F2 | Assumed prerequisite | A tool, file, install, or prior step the reader is assumed to have but was never told to get. |
| F3 | Order break | A step references something introduced later, or the sequence cannot be followed linearly. |
| F4 | Ambiguous instruction | A directive with two+ plausible readings; the reader must guess. |
| F5 | Silent success criterion | No way to tell whether a step worked before moving on. |
| F6 | Entry-point gap | Unclear where to even start, or which of N paths applies to "someone like me". |
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 · 108 lines · 117 tokens per session scan A 41c80ab14a5c
beginner is an agent published in the GitHub repository chrono-meta/forge-harness (30 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 1,380 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…