drift-intent

A workflow for recording code changes as Drift intents instead of ordinary Git commits. An intent records why a change exists, including its prompt, model, and verification details.

In plain words
What is it for?
Use it in repositories containing a .drift directory to inspect status, create intent-based commits, handle no-change results, store prompt information, and run later verification.
Why use it?
It preserves the reasoning and origin behind code changes, not just the final diff. It also checks syntax before committing and can record a command used to verify the change.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,133 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 $0.00053 $0.01133
Opus 5 $0.00026 $0.00566
Sonnet 5 $0.00011 $0.00227
Haiku 4.5 $0.00005 $0.00113

Measured 2d ago against content hash ac141cd08ba4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drift-intent 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 2d 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/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift intents

Use the drift CLI instead of a bare git commit whenever the repository has a .drift/ directory (check with ls .drift or drift doctor). Drift records why code exists — the prompt, model and provenance — not just what changed.

status — where are we?

drift status

Reports the repo state (intents, head, prompt mode, encryption, git branch) and the next step. Run it first in an unfamiliar checkout — if Drift is not initialized it says so and tells you to run drift init.

realize — commit with intent

drift realize -p "<prompt: what and why>" --agent --model <model>
  • Broken syntax is rejected before any commit (exit 2): fix the code, retry.
  • Secrets in prompts are redacted automatically; never paste keys anyway.
  • Exit 3 means there was nothing to commit (E_NO_CHANGES).
  • --verify-cmd "<cmd>" records a verification command re-run by drift verify.
  • Prompt storage is controlled by [prompts] mode in .drift/config.toml: commit-summary (default — full prompt only in local .drift/, git commit carries a safe Intent:/Model:/Verification: summary), full (prompt also in the commit message), none (prompt stored nowhere).

blame / context — trace intent

drift blame src/auth.ts --function refreshToken
drift context src/auth.ts            # hydrate reasoning for a file

blame resolves the intent whose commit touched the function — a body-only edit of a pre-Drift function reports "pre-Drift baseline".

verify / replay

drift verify <intent-id>         # re-run the recorded --verify-cmd
drift replay --checkout          # restore a prior cognitive state (agentState)

doctor / export

drift doctor                     # health check; detects corrupt .drift store (exit 5)
drift export                     # portable JSON export of all intents

If doctor reports corruption, never edit .drift/ by hand — re-run drift doctor after fixing, or restore from git history.

Read the full file on GitHub · 118 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. 2d ago First seen · 118 lines · 53 tokens per session scan A ac141cd08ba4

Subscribe to this mod's changes

drift-intent is a skill published in the GitHub repository lilcipherx/drift (4 stars, last pushed 15d ago), licensed MIT. It adds 53 tokens to every session and 1,133 once invoked, about $0.0003 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

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…

anthropics/claude-plugins-official · 82 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

offensive-c2-frameworks

Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…

SnailSploit/Claude-Red · 250 tokens

twitter-reader

Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…

himself65/finance-skills · 161 tokens

quick-recap

Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.

BuilderIO/skills · 37 tokens