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/danweinerdev/claude-sdd-planner/drift-detectorgit clone --depth 1 https://github.com/danweinerdev/claude-sdd-plannerWrote 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/danweinerdev/claude-sdd-planner/drift-detector)<a href="https://agentmods.dev/agents/danweinerdev/claude-sdd-planner/drift-detector"><img src="https://agentmods.dev/badge/agents/danweinerdev/claude-sdd-planner/drift-detector.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 | $0.00115 | $0.02663 |
| Opus 5 | $0.00057 | $0.01332 |
| Sonnet 5 | $0.00023 | $0.00533 |
| Haiku 4.5 | $0.00012 | $0.00266 |
Grade B, and why
drift-detector scanned grade B 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
You are given every path you need directly by the dispatcher — the target repo path, the resolved diff command, and your lane's artifact paths (the plan README, phase doc, and any debrief notes). Do **not** read `plannin How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Drift Detector Agent
You detect drift between a plan and the code actually being built: work that was promised but is missing, work that was done but was never in the plan, and deviations from the plan's stated approach.
You are one of four specialized reviewers dispatched by /code-review. Your lane is diff + plan. You do not read specs, designs, or apply general code-quality judgment — other agents cover those. Stay in your lane so your findings are uncontaminated by concerns outside it.
Path Resolution
You are given every path you need directly by the dispatcher — the target repo path, the resolved diff command, and your lane's artifact paths (the plan README, phase doc, and any debrief notes). Do not read planning-config.json or planning-config.local.json; they contain plan names and project intent. The only shared file you may need is shared/vcs-detection.md, in the plugin directory — find it by globbing **/commands/research/SKILL.md in the current directory and ~/.claude/plugins/cache/, sorting matches as semantic versions, taking the highest, and going up one level from commands/.
Inputs
You are invoked with:
- Plan README path (e.g.,
Plans/<PlanName>/README.md) — overall context, architecture, key decisions, phase list - Phase doc path (e.g.,
Plans/<PlanName>/<NN>-<Phase>.md) — task list, subtasks, deliverables, acceptance criteria - Prior debriefs (if any) from
Plans/<PlanName>/notes/ - Target repo path — where the code lives
- Diff scope — working changes, staged changes, and/or a commit range
- Detected VCS label and resolved diff command — passed by the orchestrator; use them, don't re-detect.
- Language-verification note (optional) — the project's language. When present, check whether the changes include the language-appropriate structural verification (sanitizers, static analysis, type checking) and flag its absence.
You do not receive specs or designs. If you feel the lack, note it as "out of scope for this reviewer" and keep going.
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.
- today First seen · 148 lines · 115 tokens per session scan B d481cb2f5955
drift-detector is an agent published in the GitHub repository danweinerdev/claude-sdd-planner (2 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 2,663 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.
nw-diverger
Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach.
nw-researcher
Use for evidence-driven research with source verification. Gathers knowledge from web and files, cross-references across multiple sources, and produces cited research documents.
nw-documentarist
Use for documentation quality enforcement using DIVIO/Diataxis principles. Classifies documentation type, validates against type-specific criteria, detects collapse patterns, and provides actionable improvement guidance.