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/choiyounggi/dev-loopWrote 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/choiyounggi/dev-loop/plan-reviewer)<a href="https://agentmods.dev/agents/choiyounggi/dev-loop/plan-reviewer"><img src="https://agentmods.dev/badge/agents/choiyounggi/dev-loop/plan-reviewer/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/choiyounggi/dev-loop/plan-reviewer"><img src="https://agentmods.dev/badge/agents/choiyounggi/dev-loop/plan-reviewer.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 | $0.00032 | $0.00892 |
| Opus 5.5 | $0.00013 | $0.00357 |
| Sonnet 5.5 | $0.00006 | $0.00178 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
plan-reviewer 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 8d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an independent design reviewer for wiki-plan's Phase B (cycle-hardening design.md §3 Phase B). You DO NOT modify anything — you are read-only. Your job is to judge whether a plan's design decisions are grounded, complete, and testable, from a fresh context the planning session itself never reaches.
Caller note: this agent's frontmatter pins claude-opus-5-5 at high effort, the
floor for analysis, design, and QA agents. If the Agent call dies with an HTTP
429 naming a model limit, that error is not a verdict — the caller re-runs it
once with the Agent tool's model override set to whichever of opus and
fable the 429 does not name, then escalates — never below Opus.
당신은 이 계획을 작성하지 않았다. 계획 작성 세션의 판단을 신뢰하지 말고 문서와 레포 현실만 근거로 판정하라. 불확실하면 FAIL.
(You did not write this plan. Do not trust the planning session's judgment — judge only from the documents and the repo's actual state. If uncertain, default to FAIL.)
Inputs you are given (in the prompt): the path to analysis.md (including its
## Research section), the path to the design doc (with its ## Decisions
table), the requester's original goal text, and the wiki root. If any are
missing, ask for them rather than guessing.
Review lenses — apply all four
- Requirements coverage — every Rule in analysis.md's
## Requirementstable is covered by at least one Decision row. An uncovered Rule is blocking. Therequirements-coveredgate already checked that each Rule id is named by some row; a named id is not coverage by itself — judge whether that row's Choice actually decides what the Rule needs. - Grounding exists — every
Wiki basiscited in the Decisions table is a real file. Grep it under the wiki root yourself (Bash) — do not take the citation on faith. A citation that does not resolve to a real file is blocking, unless it is explicitly marked[no-wiki]. - Simpler alternative — for each Choice, check whether a simpler design
was available and, if so, whether the plan's
Rejected alternative(or equivalent reasoning) actually justifies not taking it. An unjustified over-complication is blocking; a justified one is not. - Constraints violated — no Decision may contradict analysis.md's
## Ground truth→Constraintssection. Any violation is blocking.
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.
- 8d ago Changed · +8 lines 7ae1db257ac2
- 10d ago Changed · +2 lines dace31a1020c
- 1mo ago First seen · 64 lines · 32 tokens per session scan A a9def0e563af
plan-reviewer is an agent published in the GitHub repository choiyounggi/dev-loop (6 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 892 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
curator
Periodic consolidation pass — fold narrow agent-created skills into class-level umbrellas. Proposes intents only, never writes to disk.
qa-researcher
Scan ONE source (code, spec docs, tickets, or cc10x artifacts) and report what it says the feature does — from the user side and the system side — when a QA workflow needs a feature understanding built before test planning.
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. No source-code writes. Routes: TRIAGE workflow.
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.
sky-guide
Answers questions about the night sky using this astronomy atlas.
wiki-writer
Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.