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-featuregit clone --depth 1 https://github.com/sapientpants/deepsource-mcp-serverWhat 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 | $0.00959 |
| Opus 5 | $0.00000 | $0.00479 |
| Sonnet 5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
spec-feature 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec a Feature
You are about to create a feature specification in Gherkin format and turn it into a GitHub issue ready for implementation.
Process
-
Gather Requirements
- Ask the user for the feature name and description if not provided
- Understand the business value and user needs
- Identify scope, non-goals, and risks
-
Write Gherkin Specification Create a comprehensive specification including:
- Feature name and description
- Background (if needed)
- Scenarios using Given/When/Then format
- Examples with data tables where appropriate
- Acceptance Criteria
- Non-Goals (what this feature won't do)
- Risks & Mitigations
- Technical Considerations
-
Format as GitHub Issue Structure the issue with:
- Clear title:
feat: [Feature Name] - Labels:
enhancement,needs-implementation - Milestone (if applicable)
- Complete Gherkin specification in the body
- Testing requirements
- Clear title:
-
Create the Issue Use the
ghCLI to create the issue:gh issue create --title "feat: [Feature Name]" \ --body "[Full specification]" \ --label enhancement \ --label needs-implementation
Template for Issue Body
## Feature: [Feature Name]
### Business Value
[Describe the business value and user benefit]
### User Story
As a [type of user]
I want [goal/desire]
So that [benefit/value]
### Gherkin Specification
```gherkin
Feature: [Feature Name]
[Feature description explaining the feature's purpose]
Background:
Given [common preconditions for all scenarios]
Scenario: [Happy path scenario]
Given [initial context]
When [action/event]
Then [expected outcome]
And [additional outcomes]
Scenario: [Edge case or error scenario]
Given [initial context]
When [action/event]
Then [expected outcome]
Scenario Outline: [Parameterized scenario if needed]
Given [context with <parameter>]
When [action with <parameter>]
Then [outcome with <expected>]
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.
- 2d ago First seen · 160 lines · 0 tokens per session scan A 308a4dd60905
spec-feature 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 959 tokens. 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 2026-08-31.
Other commands, from other repositories
methodology
View your cognitive methodology profile and reasoning patterns.
release
Comprehensive workflow for releasing a new version of the VectorMCP Ruby gem following best practices.
compile
Compile a FIBER decision context (world + query) and report the oracle verdict, omission accounting, and certificate digest faithfully.
onboard
You are running the DataWorkers onboarding flow. Guide the user through getting started with the DataWorkers MCP platform.
safety-check
Verify the EA1 safety gate blocks all destructive actions on a page.
2-spec
Command "2-spec" from clchinkc/document-mcp, covering requirements gathering generation, behavioral scenario generation (optional), design document creation generation and implementation planning generation.