fast-follow

fast-follow is a skill for Claude Code, Codex from OpenAgentsInc/openagents. It costs 34 tokens per session (1,786 once invoked), scanned A, original, Apache-2.0.

A process for studying another software project and turning the lessons into source-grounded research, gap assessments, issue candidates, or separately approved implementation work. It follows a project's FastFollowSpec, which defines what may be learned and changed.

In plain words
What is it for?
Use it when a repository asks for a fast follow, to inspect its governing specifications, compare the target project with an upstream one, and produce approved follow-up work.
Why use it?
It keeps lessons from an upstream project separate from authority to implement, verify, release, deploy, spend money, or make public claims.

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/openagentsinc/openagents/fast-follow
Any agent
npx skills add OpenAgentsInc/openagents --skill fast-follow
Clone the repo
git clone --depth 1 https://github.com/OpenAgentsInc/openagents

Made for: Claude Code, Codex.

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 fast-follow

README.md
[![agentmods](https://agentmods.dev/badge/skills/openagentsinc/openagents/fast-follow.svg)](https://agentmods.dev/skills/openagentsinc/openagents/fast-follow)
Your own site
<a href="https://agentmods.dev/skills/openagentsinc/openagents/fast-follow"><img src="https://agentmods.dev/badge/skills/openagentsinc/openagents/fast-follow.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,786 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 5.1 $0.00034 $0.01786
Opus 5 $0.00017 $0.00893
Sonnet 5 $0.00007 $0.00357
Haiku 4.5 $0.00003 $0.00179

Measured 6d ago against content hash ad126af1c00b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

fast-follow 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 6d 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.

.agents/skills/fast-follow/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fast Follow

Use this skill when a project has a FASTFOLLOW.md, the user asks to fast follow another project, or Full Auto selects Fast Follow as its work source. FastFollowSpec declares learning intent. It never grants implementation, verification, release, spend, deployment, or public-claim authority.

Resolve authority first

  1. Resolve the nearest applicable AGENTS.md and INVARIANTS.md.
  2. Resolve FASTFOLLOW.md beside that AGENTS.md, or the exact repository-relative path named by it.
  3. Read the FastFollowSpec completely, including every typed block needed by the selected directive.
  4. Validate the format version, lifecycle, stable IDs, source/lesson refs, target scope, work stage, write boundary, and implementation requirements.
  5. Read current ProductSpec, AssuranceSpec, roadmap, issue, claim, and receipt authorities relevant to the target scope.

If work_generation.initial_program exists, bind its exact strategy artifact and select the first directive in directive_order without a durable terminal or blocked disposition. Use its default_stage. Advance only under its declared transition and exhaustion policy. Do not silently substitute a higher-priority catalog directive.

If the spec is missing, malformed, unsupported, escaped, stale, or internally inconsistent, report a typed blocker. Do not reconstruct policy from nearby prose, filenames, teardown advice, or an older run.

Choose exactly one lane

The initiating request or an admitted run policy selects one lane:

  • research — pin and study source material. Write only configured study, gap, candidate, receipt, or teardown artifacts. Never edit product code.
  • gap_analysis — compare a pinned StudyPacket with an exact target revision and current authority. Produce evidence, not an adoption verdict.
  • candidate_proposal — produce one deduped issue/work-packet proposal with target constraints and proof refs. Do not open or admit it unless separately authorized.
  • implementation — consume one already admitted issue, accepted plan, or work packet after claim/worktree/dependency checks. Implement the smallest target-native adaptation and run target-local proof. Or
  • verification — execute the target's reviewed proof design and report axes without claiming acceptance.

Read the full file on GitHub · 187 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. 6d ago First seen · 187 lines · 34 tokens per session scan A ad126af1c00b

Subscribe to this mod's changes

fast-follow is a skill published in the GitHub repository OpenAgentsInc/openagents (446 stars, last pushed today), licensed Apache-2.0. It adds 34 tokens to every session and 1,786 once invoked, about $0.0002 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 2026-08-30.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens