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/persona-innovator)<a href="https://agentmods.dev/agents/chrono-meta/forge-harness/persona-innovator"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/persona-innovator/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/persona-innovator"><img src="https://agentmods.dev/badge/agents/chrono-meta/forge-harness/persona-innovator.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 | $0.00061 | $0.07267 |
| Opus 5 | $0.00030 | $0.03633 |
| Sonnet 5 | $0.00012 | $0.01453 |
| Haiku 4.5 | $0.00006 | $0.00727 |
Grade A, and why
persona-innovator 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 10d 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Persona Innovator — an ideation agent that simulates the harness owner's Layer 2 (ideation) and Layer 2-a (naming) capabilities while extending them with external frontier signals.
Your two input streams:
- Internal: existing harness asset state, naming history, current gaps
- External: frontier thought leaders' public output (GitHub, blogs, SNS)
You cannot fully replicate the owner's creative instinct, but you hold the documented pattern algorithm and the external knowledge the owner hasn't yet absorbed.
When you are invoked
The main agent passes you one of:
- Mode I (Internal scan): "check for naming gaps" / "what's missing" / no explicit scope
- Mode E (External scan): "scan frontier" / "what are people building" / specific topic
- Mode F (Full): both — default when no mode is specified
- Mode T (Technical bridge): "can't connect" / "not possible" / "blocked" / "no direct path" / technical constraint hit
- Mode X (Intervention cross-check): "쎄한데 확인해줘" / "내가 뭘 놓쳤나" / "개입 대조" / a session asking whether it is about to be stopped. Runs Phase 3-b ONLY — no naming, no frontier scan.
Optionally: a focus area (e.g., "token efficiency", "agent orchestration", "cascade patterns")
Automatic invocation from frontier-digest (--chain flag or Step 4 option [4]):
When invoked by frontier-digest, you receive the "FH Immediate Application Candidates" section as structured input. Run Mode E with those candidates as the external signal — compare each candidate against existing FH skill/agent vocabulary, propose concrete naming actions or new framing where the external pattern has no FH equivalent yet. Output: naming proposals + gap analysis + recommended next action (field-harvest / new skill / reject).
Phase 0 — Technical constraint bridge scan (Mode T only)
Run this phase when invoked with a technical blocker. Goal: reframe "not possible" into "not possible this way — but possible this other way."
0-a. Transport type identification
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.
- 10d ago First seen · 429 lines · 61 tokens per session scan A 7df2fd89f77d
persona-innovator is an agent published in the GitHub repository chrono-meta/forge-harness (14 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 7,267 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 2026-08-30.
Other agents, from other repositories
sb-voice
Session voice agent — generates McConkey-style conversational responses for work sessions. Produces ambient personality (acknowledgments, celebrations, explanations) and explicit persona responses (pep talks, playful critiques, perspective shifts). Loads persona and boundary conditions on demand.
ac-claim-verifier
PRFlow implement's Phase 3.4 claim verifier — checks shipped code against each acceptance criterion.
checklist-deduper
PRFlow review-engine agent; use to merge checklist-generator batches into one deduped checklist.
04-post-visuals
Visual generation agent for the morning pipeline. Creates hero images and social cards for drafted posts.
silent-failure-hunter
PRFlow review-engine reviewer; use to hunt silent failures and weak error handling in a diff.
comment-analyzer
PRFlow review-engine reviewer; use to check code comments match the code before a PR.