drift-protection

drift-protection is a skill for Claude Code, Codex from dormstern/forge. It costs 87 tokens per session (1,231 once invoked), scanned A, original, MIT.

A product-direction check that reviews the last five completed features against the project's identity, architecture rules, contracts, and rework patterns.

In plain words
What is it for?
Use it during build work or before a release to decide whether to continue, discuss changes, pivot, or stop for a contract issue.
Why use it?
It helps detect when ongoing development is moving away from the intended users, goals, or technical boundaries.

Skill for Claude CodeCodex

Part of the forge plugin — 10 skills, 15 commands, 9 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add skills/dormstern/forge/drift-protection
Any agent
npx skills add dormstern/forge --skill drift-protection
Clone the repo
git clone --depth 1 https://github.com/dormstern/forge

Made for: Claude Code, Codex.

Or install forge, the plugin that ships this one along with the rest of its 10 skills, 15 commands, 9 agents, 1 hook.

Wrote 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.

agentmods badge for drift-protection

README.md
[![agentmods](https://agentmods.dev/badge/skills/dormstern/forge/drift-protection.svg)](https://agentmods.dev/skills/dormstern/forge/drift-protection)
Your own site
<a href="https://agentmods.dev/skills/dormstern/forge/drift-protection"><img src="https://agentmods.dev/badge/skills/dormstern/forge/drift-protection.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,231 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00087 $0.01231
Opus 5 $0.00044 $0.00616
Sonnet 5 $0.00017 $0.00246
Haiku 4.5 $0.00009 $0.00123

Measured 3d ago against content hash 65374b516d57, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drift-protection 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 3d 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.

skills/drift-protection/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Protection

Drift checks are the single most-distinctive primitive in PM mode. They're the reason the framework can run forever without slowly building the wrong product.

Cadence

  • Auto: every 5 completed features during /forge:build. The orchestrator dispatches the drift-detector agent automatically.
  • Manual: /forge:drift any time — after a refactor, before a release, after an identity update.

The 6 checks (per feature, last 5 done)

# Check What's being audited
1 Serves WHO? Does this improve life for the IDENTITY.md persona?
2 Serves JOB? Does this make the JOB easier or remove a step?
3 Violates NEVER? Does any aspect of this do something the NEVER list forbids?
4 Respects Architecture Constraints? Right module, existing patterns, no unnecessary cross-module coupling?
5 Respects contracts? (if contract_mode != "none") API shape preserved, schema additive, events versioned?
6 Is this rework? Did it modify recently-shipped code? Pattern across multiple features?

Each check is a verdict: YES / NO / DRIFT.

Verdict ladder

Verdict Meaning
CLEAR All 6 checks YES across all 5 features
DRIFT One feature violates WHO/JOB/NEVER/architecture
CONTRACT_VIOLATION Breaks a published contract without an approved migration path
ARCHITECTURE_DEGRADATION Adds complexity to hot paths or crosses module boundaries unnecessarily
REWORK_PATTERN 2+ rework flags across last 5 features

Recommendation matrix

Recommendation Trigger
CONTINUE All clear, no stabilization indicators
DISCUSS One DRIFT, surface to user, no halt
PIVOT Pattern of DRIFT — identity may need to evolve
CONTRACT_HALT CONTRACT_VIOLATION — halt the release until resolved
STABILIZE Stabilization indicators firing — next SHAPE should be a stabilization release

Read the full file on GitHub · 100 lines

Changes

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.

  1. 3d ago First seen · 100 lines · 87 tokens per session scan A 65374b516d57

Subscribe to this mod's changes

drift-protection is a skill published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 1,231 once invoked, about $0.0004 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens