openspec-replan

openspec-replan is a skill for Claude Code from digital-stoic-org/agent-skills. It costs 33 tokens per session (1,399 once invoked), scanned A, original, MIT.

A replanning tool for OpenSpec changes, where software work is tracked through structured proposals and tasks. It revises the plan when work is blocked or has moved beyond its original scope.

In plain words
What is it for?
Use it to analyze a blocked or drifting change, propose revised tasks or a new direction, and apply the revision after confirmation.
Why use it?
It provides a controlled way to respond to blockers and direction changes without losing the reasoning behind the project plan.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the openspec plugin — 9 skills shipped together

Good fit Use it to analyze a blocked or drifting change, propose revised tasks or a new direction, and apply the revision after confirmation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/digital-stoic-org/agent-skills/openspec-replan
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.

Any agent
npx skills add digital-stoic-org/agent-skills --skill openspec-replan
Clone the repo
git clone --depth 1 https://github.com/digital-stoic-org/agent-skills

Made for: Claude Code.

Or install openspec, the plugin that ships this one along with the rest of its 9 skills.

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 openspec-replan

README.md
[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-replan/github.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-replan)
Your own site
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-replan"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-replan/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for openspec-replan

Your own site · 80×15
<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/openspec-replan"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/openspec-replan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 4
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00033 $0.01399
Opus 5.5 $0.00013 $0.00560
Sonnet 5.5 $0.00007 $0.00280
Haiku 4.5 $0.00003 $0.00140

Measured 1mo ago against content hash 24feb44a544a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openspec-replan 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 1mo 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.

openspec/skills/openspec-replan/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec Replan

Adaptive refinement skill for blocked or drifted changes. Proposes revised tasks or pivots.

⚠️ AskUserQuestion Guard

CRITICAL: After EVERY AskUserQuestion call, check if answers are empty/blank. Known Claude Code bug: outside Plan Mode, AskUserQuestion silently returns empty answers without showing UI.

If answers are empty: DO NOT proceed with assumptions. Instead:

  1. Output: "⚠️ Questions didn't display (known Claude Code bug outside Plan Mode)."
  2. Present the options as a numbered text list and ask user to reply with their choice number.
  3. WAIT for user reply before continuing.

Workflow: Analyze → Propose → Confirm → Apply

flowchart LR
    A["Analyze blocker/drift"] --> B["Read context"]
    B --> C["Propose revisions"]
    C --> D{"User approval?"}
    D -->|Yes| E["Apply changes"]
    D -->|No| F["Discard"]
    E --> G["Document blocker"]

    classDef action fill:#C8E6C9,stroke:#388E3C,color:#000
    classDef gate fill:#E1BEE7,stroke:#7B1FA2,color:#000
    classDef discard fill:#FFCDD2,stroke:#D32F2F,color:#000

    class A,B,C,E,G action
    class D gate
    class F discard

Critical: Always wait for user confirmation before applying changes (ask_first trust zone).

Guardrails

Trust Zone: ask_first (all changes require human approval)

Always ask before:

  • Modifying tasks.md
  • Modifying proposal.md
  • Archiving files
  • Any scope changes

Scope deviation threshold: >20%

  • If openspec-reflect reports >20% drift, suggest replan
  • Show deviation calculation in proposal

Minimal change preference:

  • Count affected vs unaffected tasks
  • If <50% affected, revise only those tasks
  • If >50% affected, consider pivot instead

Commands

replan

Revise tasks when implementation is blocked.

Input: $ARGUMENTS = change-id [blocker-description]

Workflow:

  1. Read openspec/changes/{change-id}/tasks.md, proposal.md, specs
  2. Identify blocker (from argument or ask user)
  3. Analyze which tasks are affected
  4. Minimal change preference: Revise only affected tasks, not entire list
  5. Propose revised tasks with blocker context
  6. Wait for user approval before applying
  7. If approved: Update tasks.md with revisions
  8. Document blocker as comment in tasks.md

Read the full file on GitHub · 209 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. 1mo ago First seen · 209 lines · 33 tokens per session scan A 24feb44a544a

Subscribe to this mod's changes

openspec-replan is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 12d ago), licensed MIT. It adds 33 tokens to every session and 1,399 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.

Related

Other skills, from other repositories