spec-chore

spec-chore is a command for Claude Code from sapientpants/deepsource-mcp-server. It costs 0 tokens per session (1,442 once invoked), scanned B, original, MIT.

A command for planning a software maintenance task, known as a chore, and preparing it as a GitHub issue. It gathers requirements, defines the desired result and acceptance checks, and uses the GitHub command-line tool to create the issue.

In plain words
What is it for?
Use it to document technical-debt work, define maintenance steps and boundaries, and create a labeled GitHub issue for implementation.
Why use it?
It turns an informal maintenance request into an implementation-ready task with clear scope, impacts, and validation requirements.

Command for Claude Code

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 commands/sapientpants/deepsource-mcp-server/spec-chore
Clone the repo
git clone --depth 1 https://github.com/sapientpants/deepsource-mcp-server

Made for: Claude Code.

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 spec-chore

README.md
[![agentmods](https://agentmods.dev/badge/commands/sapientpants/deepsource-mcp-server/spec-chore.svg)](https://agentmods.dev/commands/sapientpants/deepsource-mcp-server/spec-chore)
Your own site
<a href="https://agentmods.dev/commands/sapientpants/deepsource-mcp-server/spec-chore"><img src="https://agentmods.dev/badge/commands/sapientpants/deepsource-mcp-server/spec-chore.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,442 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.01442
Opus 5 $0.00000 $0.00721
Sonnet 5 $0.00000 $0.00288
Haiku 4.5 $0.00000 $0.00144

Measured 3d ago against content hash fc61be108884, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

spec-chore scanned grade B with 1 finding 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- [ ] Build succeeds without warnings
.claude/commands/spec-chore.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec a Chore

You are about to create a chore specification and turn it into a GitHub issue ready for implementation.

Process

  1. Gather Requirements

    • Ask the user for the chore name and description if not provided
    • Understand the maintenance goal and technical debt being addressed
    • Identify scope, constraints, and potential impacts
  2. Write Chore Specification Create a comprehensive specification including:

    • Chore name and description
    • Current State (what's wrong/needs improvement)
    • Desired State (what success looks like)
    • Implementation Steps (clear, actionable tasks)
    • Acceptance Criteria
    • Out of Scope (what this chore won't address)
    • Impact Analysis (what might be affected)
    • Technical Details
  3. Format as GitHub Issue Structure the issue with:

    • Clear title: chore: [Chore Name]
    • Labels: chore, maintenance, technical-debt (as appropriate)
    • Milestone (if applicable)
    • Complete specification in the body
    • Testing/validation requirements
  4. Create the Issue Use the gh CLI to create the issue:

    gh issue create --title "chore: [Chore Name]" \
      --body "[Full specification]" \
      --label chore \
      --label maintenance
    

Template for Issue Body

## Chore: [Chore Name]

### Motivation

[Explain why this chore is needed - technical debt, maintenance, performance, etc.]

### Current State

[Describe the current situation that needs improvement]

- Problem 1: [specific issue]
- Problem 2: [specific issue]
- Technical debt: [if applicable]

### Desired State

[Describe what the codebase should look like after this chore]

- Improvement 1: [specific outcome]
- Improvement 2: [specific outcome]
- Resolved debt: [if applicable]

### Implementation Steps

1. **Step 1**: [Clear action]
   - Sub-task 1.1
   - Sub-task 1.2

2. **Step 2**: [Clear action]
   - Sub-task 2.1
   - Sub-task 2.2

3. **Step 3**: [Clear action]
   - Sub-task 3.1
   - Sub-task 3.2

### Acceptance Criteria

- [ ] All deprecated dependencies updated
- [ ] All obsolete code removed
- [ ] Documentation updated to reflect changes
- [ ] No functionality broken (all tests pass)
- [ ] Performance metrics maintained or improved
- [ ] Code quality metrics improved

### Out of Scope

- This chore will NOT [explicitly excluded work]
- Future improvements: [related but deferred work]

### Impact Analysis

#### Systems Affected

- Component A: [impact description]
- Component B: [impact description]

#### Risk Assessment

- **Low Risk**: [areas with minimal impact]
- **Medium Risk**: [areas needing careful testing]
- **High Risk**: [critical areas requiring extra attention]

### Technical Details

#### Dependencies to Update

- Package A: from version X to Y
- Package B: from version X to Y

#### Files to Modify

- `path/to/file1.ts`: [change description]
- `path/to/file2.ts`: [change description]

#### Configuration Changes

- Config A: [change description]
- Config B: [change description]

### Validation Requirements

- [ ] All existing tests pass
- [ ] Build succeeds without warnings
- [ ] Linting passes without errors
- [ ] Performance benchmarks show no regression
- [ ] Manual testing of affected areas
- [ ] Security scan shows no new vulnerabilities

### Rollback Plan

If issues are discovered:

1. [Step to revert changes]
2. [Step to restore previous state]
3. [Verification steps]

### Definition of Done

- [ ] All acceptance criteria met
- [ ] Code changes reviewed and approved
- [ ] Documentation updated where necessary
- [ ] No increase in technical debt
- [ ] Changeset added (if applicable)
- [ ] CI/CD pipeline passes

Read the full file on GitHub · 252 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 · 252 lines · 0 tokens per session scan B fc61be108884

Subscribe to this mod's changes

spec-chore is a command published in the GitHub repository sapientpants/deepsource-mcp-server (7 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,442 tokens. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.