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.
npx agentmods add commands/sapientpants/deepsource-mcp-server/spec-choregit clone --depth 1 https://github.com/sapientpants/deepsource-mcp-serverWrote 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.
[](https://agentmods.dev/commands/sapientpants/deepsource-mcp-server/spec-chore)<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>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.
| Model | Per session | Once 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 |
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 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
-
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
-
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
-
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
- Clear title:
-
Create the Issue Use the
ghCLI 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
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.
- 3d ago First seen · 252 lines · 0 tokens per session scan B fc61be108884
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.
Other commands, from other repositories
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
compile
Compile a FIBER decision context (world + query) and report the oracle verdict, omission accounting, and certificate digest faithfully.
10-optimization-finalization
Comprehensive Optimization: Multi-agent optimization, PRD improvement, documentation consolidation, and production-ready finalization.
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.