specrew-refocus

A recovery skill that reloads the rules for Specrew's current work stage when the agent loses context. It can be used after a conversation reset or when the agent's process starts drifting.

In plain words
What is it for?
Use it to restore stage-specific guidance, check the refocus system's status, or reset its safety breaker.
Why use it?
Long sessions, context compression, or restarts can make an agent forget important working rules and its place in a process.

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

Made for: Claude Code, Codex.

Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,092 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 $0.00166 $0.01092
Opus 5 $0.00083 $0.00546
Sonnet 5 $0.00033 $0.00218
Haiku 4.5 $0.00017 $0.00109

Measured 2d ago against content hash 2776799e67a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specrew-refocus 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.

.agents/skills/specrew-refocus/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

specrew-refocus

Type: Recovery + Discipline Skill Schema: v1 Status: Active drift-remediation surface (Feature 171)

Purpose

Re-load scoped Specrew methodology discipline into context ON DEMAND — the manual recovery surface for agent drift. Use it when context feels degraded: after a compaction, after a host restart, deep in a long session, or whenever you are about to act on methodology you are reconstructing from memory instead of from the source.

The same payload engine also fires AUTOMATICALLY: boundary syncs append the incoming stage's digest to their output (every host), and on hook-capable hosts, post-compaction and session-start events re-inject discipline without anyone asking. Treat any [specrew-refocus] block you see in tool output as binding stage discipline, not informational noise.

When to Use

  • You notice drift: reviews going shallow, boundary discipline slipping, role rules fuzzy.
  • A compaction or /clear just happened and the lifecycle position needs re-grounding.
  • You are entering a new lifecycle stage and want its discipline fresh (--boundary <stage>).
  • You are diagnosing the refocus automation itself (--status, --reset-breaker).

Invocation Contract

# All invocations run the project-local deployed engine:
pwsh -NoProfile -ExecutionPolicy Bypass -File .specify/extensions/specrew-speckit/scripts/refocus.ps1 [args]
Arguments Payload
(none) always-true core + the CURRENT stage's discipline digest
--boundary <stage> always-true core + the named stage digest (specify, clarify, plan, tasks, before-implement, implement, review-signoff, retro, iteration-closeout, feature-closeout)
--role <name> the named role charter (e.g. reviewer, planner)
--shape-catalog the Form-Without-Runtime-Compliance Shape catalog
--everything the full digest corpus (heavy — warned)
--compact-instructions a paste-ready /compact preserve-list built from live lifecycle state — use it at heavy-context boundary stops to compact at a clean watershed
--status the whole operational truth: env kill switch, per-trigger catalog flags, per-session breaker state, injection-journal tail
--reset-breaker clears tripped circuit-breaker flags for this project's sessions

Read the full file on GitHub · 57 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 57 lines · 166 tokens per session scan A 2776799e67a3

Subscribe to this mod's changes

specrew-refocus is a skill published in the GitHub repository alonf/specrew (54 stars, last pushed 3d ago), licensed MIT. It adds 166 tokens to every session and 1,092 once invoked, about $0.0008 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

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

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

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 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