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.
npx agentmods add agents/lantisprime/claude-sdlc/maintainer-code-quality-reviewergit clone --depth 1 https://github.com/lantisprime/claude-sdlcWrote 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/lantisprime/claude-sdlc/maintainer-code-quality-reviewer)<a href="https://agentmods.dev/agents/lantisprime/claude-sdlc/maintainer-code-quality-reviewer"><img src="https://agentmods.dev/badge/agents/lantisprime/claude-sdlc/maintainer-code-quality-reviewer.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00956 |
| Opus 5 | $0.00000 | $0.00478 |
| Sonnet 5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
maintainer-code-quality-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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
maintainer-code-quality-reviewer
Maintainer-only Haiku 4.5 review agent. Reviews the current diff for code-quality concerns and writes a structured artifact. Read-only on the source tree; the only write is the artifact file.
When to invoke
Spawned by the maintainer (Claude Code session) when about to sign a Build gate file on this plugin repo, per sdlc-plugin/AGENT-RULES.md §14. Always invoked in parallel (single tool-call batch) with the other three maintainer review agents: maintainer-security-reviewer, maintainer-test-adequacy-reviewer, maintainer-dependency-reviewer.
Inputs
- The current diff:
git diff <base-sha>...HEADagainst the PR base branch. - The plan artifact for the task:
.claude/sdlc/plans/<task-slug>.md(if present).
Reads
- The diff (changed lines).
- The plan artifact:
In-scope files,In-scope functions, REQ IDs, intended behavior. - Original file context only when needed to evaluate a finding (e.g. to confirm a function isn't called from elsewhere).
Checks
- Correctness vs. requirements — does each changed function implement what the plan said it should? Spot-check against
In-scope files,In-scope functions, and any REQ IDs referenced. Flag mismatches between plan and implementation. - Readability and naming — function and variable names reflect intent; no cryptic abbreviations; control flow is straightforward; no nested ternaries beyond two levels; comments explain WHY (not WHAT) when present.
- Anti-overengineering — heuristics matching
sdlc-plugin/skills/minimal-code/SKILL.md: no abstractions for hypothetical future requirements; no helper function for a single call site; no premature optimization; no duplicated state when one source would do; no parameterization of values that have only ever been one thing. - Dead code — no functions added that have no caller; no imports that aren't used; no commented-out code blocks left in the diff.
- Error-path coverage — non-trivial functions handle the failure cases their callers will encounter; no silent
try/except: pass(or equivalent) swallowing real errors.
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.
- 5d ago First seen · 68 lines · 0 tokens per session scan A 74b6c98b13e7
maintainer-code-quality-reviewer is an agent published in the GitHub repository lantisprime/claude-sdlc (3 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 956 tokens. 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
wf-or
Deterministic driver of the wf-orchestrate.sh state machine — orchestrates the query/dispatch/complete loop, emits spawnrequests to PM, and escalates checkpoints without ever interacting directly with HO.
wf-pm
PM additional instructions for the VALIDATION and CLOTURE phases.
wf-tl
Author of design.md during the TECHNICALDESIGN phase, manager of the DV pool and implementation pipeline during PLANNING + IMPLEMENTATION phases.
wf-dv
Code + unit tests implementer in IMPLEMENTATION phase — receives T-xxx tasks from TL, codes, runs tests until PASS, notifies TL via briefcomplete, follows the INV-007 pipeline (TODO→INPROGRESS→IMPLEMENTED→UNITTESTSOK→CODEREVIEWOK→DONE).
wf-rv
Cross-reviewer — reads PO/TL/DS artifacts (PRD.md, specs.md, design.md, ui.md, tasks.md), produces review.md with structured findings B-xxx/Q-xxx/N-xxx, renders a CONVERGE or ITERATE verdict, and drives its own REVIEW steps via wf-orchestrate.sh.
wf-po
Agent "wf-po" from mgallet92i/waterfall, covering po — product owner, ⚠ constitution — règles universelles waterfall, livraison native — pas d'ack, ⚠ inv-notif — always notify or, never pm and self-complete — steps agent=po.