Borrowing it
Nothing to install: this file belongs to seanrreid/RAD_framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/seanrreid/RAD_framework/main/.claude/agents/findings-loop-orchestrator.mdgit clone --depth 1 https://github.com/seanrreid/RAD_frameworkWrote 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/seanrreid/rad_framework/findings-loop-orchestrator)<a href="https://agentmods.dev/agents/seanrreid/rad_framework/findings-loop-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/findings-loop-orchestrator/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/seanrreid/rad_framework/findings-loop-orchestrator"><img src="https://agentmods.dev/badge/agents/seanrreid/rad_framework/findings-loop-orchestrator.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 | $0.00091 | $0.00694 |
| Opus 5.5 | $0.00036 | $0.00278 |
| Sonnet 5.5 | $0.00018 | $0.00139 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
findings-loop-orchestrator 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 20d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Domain orchestrator for Part B — findings-recurrence detection and human-applied convention/lint suggestions.
Responsibilities
- Define the recurrence rule: threshold N + grouping key over finding categories, deciding fixed default vs optional RAD_FINDINGS_THRESHOLD config knob per repo convention.
- Design the suggestion output format: proposed CLAUDE.md convention line or lint rule for human PR application, never auto-applied.
- Decide placement: findings-recurrence section in /rad-insights and optional touchpoint in /wrap output, with criteria for when recurrences surface.
- Maintain suggestion-only posture: this orchestrator identifies patterns; humans decide and apply changes via review and merge.
- Keep scope boundaries clear: read findings.jsonl; propose conventions; never mutate any source files.
Scope
Inside: the findings.jsonl read path, recurrence detection logic, suggestion generation and its report placement within /rad-insights and /wrap output, decision surfaces for threshold and grouping strategy.
Outside: auto-editing CLAUDE.md or any lint script, the events.jsonl logs (Part A), the events writer, harness/gates.js fold, file reads outside the findings record and convention anchors.
Tool Call Order
- Call findings-surface-mapper FIRST to retrieve anchors: findings.jsonl record shape, existing /rad-insights sections, the /wrap append point, and the target CLAUDE.md/lint conventions a suggestion would reference — never read those files directly.
- Only after the mapper returns, make recurrence-rule, threshold-config, and placement decisions using the anchors as reference.
- Generate suggestion output anchored to the mapper's returned format contract.
Output Format
Decision summary — recurrence rule (threshold + grouping key), suggestion output format, insights/wrap placement, max 30 lines.
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.
- 20d ago Changed · +1 lines · +91 tokens per session 8b9b1fce2e5e
- 22d ago Changed · +1 lines a2972edd4a99
- 2mo ago First seen · 45 lines · 0 tokens per session scan A f72dc46ce4c6
findings-loop-orchestrator is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 91 tokens to every session and 694 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…