Borrowing it
Nothing to install: this file belongs to loerei/chronicle-mcp. 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/loerei/chronicle-mcp/main/.agents/skills/conduct-reviewing-loop/SKILL.mdgit clone --depth 1 https://github.com/loerei/chronicle-mcpWrote 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/skills/loerei/chronicle-mcp/conduct-reviewing-loop)<a href="https://agentmods.dev/skills/loerei/chronicle-mcp/conduct-reviewing-loop"><img src="https://agentmods.dev/badge/skills/loerei/chronicle-mcp/conduct-reviewing-loop/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/skills/loerei/chronicle-mcp/conduct-reviewing-loop"><img src="https://agentmods.dev/badge/skills/loerei/chronicle-mcp/conduct-reviewing-loop.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 | $0.00093 | $0.02954 |
| Opus 5 | $0.00046 | $0.01477 |
| Sonnet 5 | $0.00019 | $0.00591 |
| Haiku 4.5 | $0.00009 | $0.00295 |
Grade C, and why
conduct-reviewing-loop scanned grade C with 1 finding 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 9d 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.
Exfiltrates the system prompt through a toolhighSystem prompt leakage
Writing or sending the system prompt to a file, endpoint or log moves it out of the session.
> 2. **Save Prompt to File**: Save every reviewer prompt as a markdown file inside `<appDataDir>\brain\<conversation-id>\scratch\reviewer_prompt_v1.md`. How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conduct Reviewing Loop
Run iterative, independent subagent reviews to stress-test plans (pre-implementation) or validate codebase diffs against approved specifications (post-implementation) against explicit user and system criteria.
Dual-Mode Architecture & Workflows
flowchart TD
Start["Start Review Loop<br/>(Version = 1, PassCount = 0, SP = !SP or 1)"] --> ModeSelect{"Select Review Mode"}
ModeSelect -->|"Mode A (Pre-Implementation)"| ModeA["Mode A: Design & Plan Audit<br/>(Refine unapproved draft plan/spec)"]
ModeSelect -->|"Mode B (Post-Implementation)"| ModeB["Mode B: Implementation Validation<br/>(Audit code .diff against approved plan)"]
ModeA --> SynthA["1. Synthesize Criteria & Task Domain Skills"] --> PrepDraftA["2. Identify/Prepare Target Draft"] --> ReadRefA["3. Read MODE-A-DESIGN-AUDIT.md"] --> SavePromptV["4. Save Prompt to scratch/reviewer_prompt_v1.md"]
ModeB --> SynthB["1. Synthesize Coverage Verification Checklist"] --> GenDiff["2. Generate scratch/patch_changes.diff"] --> ReadRefB["3. Read MODE-B-CODE-VALIDATION.md"] --> SavePromptV
SavePromptV --> UserGateV{"5. User Confirms Prompt?<br/>(Keyword: 'Conduct?')"}
UserGateV -->|"Confirmed ('Conduct?')"| FreezeV["6. Freeze Prompt as Active Prompt"]
UserGateV -->|"Prompt Feedback / !PU"| RefinePrompt["Refine Prompt"] --> SavePromptV
FreezeV --> BlindSpawn["7. Spawn Independent Reviewer #N (Using Active Frozen Prompt)"]
BlindSpawn --> CritEval{"8. Critical Evaluation of Feedback (Main Agent)"}
CritEval -->|"Valid Edits Needed"| ResetPass["Reset PassCount = 0"] --> CheckExc{"New User Request / New Spec / !PU?"}
CheckExc -->|"No (Standard Fix)"| ApplyFix["Apply fixes (Mode A: Draft / Mode B: Code)"] --> CheckPA{"!PA Active AND Not Final PASS?"}
CheckExc -->|"Yes (!PU / Exception)"| IncVer["Version = Version + 1"] --> SavePromptNew["Save scratch/reviewer_prompt_v{Version}.md"] --> UserGateNew{"User Confirms Prompt?<br/>(Keyword: 'Conduct?')"}
UserGateNew -->|"Confirmed ('Conduct?')"| FreezeNew["Freeze v{Version} as Active Prompt"] --> ApplyFix
UserGateNew -->|"Keep Previous"| KeepPrev["Keep Previous Active Prompt"] --> ApplyFix
CheckPA -->|"Yes (!PA Set)"| PauseLoop["PAUSE: Report Edits & Await User Resume"]
CheckPA -->|"No"| BranchMode{"Mode?"}
PauseLoop -->|"User Resumes"| BranchMode
BranchMode -->|"Mode B"| Regendiff["Re-generate .diff"] --> NextIter["Iteration N = N + 1"] --> BlindSpawn
BranchMode -->|"Mode A"| NextIter
CritEval -->|"STATUS: PASS"| PassCounter{"PassCount = PassCount + 1<br/>PassCount >= SP?"}
PassCounter -->|"Yes (Final PASS)"| Present["9. Present Verified Final Output"]
PassCounter -->|"No (Not Final PASS)"| CheckPA{"!PA Active AND Not Final PASS?"}
CritEval -->|"All Points Evaluated Invalid"| JustifyUser["Document Exclusions & Report to User"] --> UserGateFinal{"User Approves Rationale?"}
UserGateFinal -->|"Approved"| Present
UserGateFinal -->|"User Rejects Rationale"| ResetPass
UserFPA["User sends !FPA Mid-Loop"] -.->|"Emergency Signal"| KillReviewer["Kill Running Reviewer #N Subagent<br/>& Discard Feedback"] -.-> PauseLoopEmergency["PAUSE: Emergency Stop & Await User Instructions"]
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 126 lines · 93 tokens per session scan C e60e43931dd5
conduct-reviewing-loop is a skill published in the GitHub repository loerei/chronicle-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 93 tokens to every session and 2,954 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (exfiltrates the system prompt through a tool). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.