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/marcelsud/spec-driven-agentic-development/executegit clone --depth 1 https://github.com/marcelsud/spec-driven-agentic-developmentWhat 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 | $0.00019 | $0.01000 |
| Opus 5 | $0.00010 | $0.00500 |
| Sonnet 5 | $0.00004 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
execute 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Feature Implementation
Feature: $ARGUMENTS
You are executing a feature implementation based on the structured specifications.
Feature Selection Logic:
-
IF a feature name is provided in
$ARGUMENTS:- TRY to find a directory in
features/that matches$ARGUMENTS. - IF no exact match is found, SEARCH for the closest directory name.
- IF a close match is found, ASK the user for confirmation: "Did you mean 'features/[found_directory_name]'? (yes/no)"
- IF user confirms, PROCEED. IF user denies, STOP and ask for the correct name.
- TRY to find a directory in
-
IF no feature name is provided:
- LIST all directories under
features/. - IF only one feature directory exists, automatically SELECT it and state which one you are using.
- IF multiple feature directories exist, LIST them and ASK the user to specify which one to proceed with.
- LIST all directories under
Context Loading:
- Once a feature is selected, READ these files into your context:
features/[selected_feature_name]/context.mdfeatures/[selected_feature_name]/requirements.mdfeatures/[selected_feature_name]/tasks.md
Your Task
Implement the feature by executing the plan in tasks.md.
Execution Process
-
Understand the Full Specification:
- Read
context.mdto understand the context and technical decisions. - Read
requirements.mdto understand the "what" (EARS requirements). - Thoroughly review
tasks.mdfor the detailed implementation plan and TDD steps.
- Read
-
ULTRATHINK & Plan Execution:
- Think hard before you execute. Create a comprehensive plan to tackle the tasks.
- Use your
TodoWritetool to break down the implementation of each task fromtasks.mdinto smaller, manageable steps. - Identify implementation patterns from the existing codebase as guided by
context.md. - Use your
TodoWritetool to create a task to run the complete test suite. All tests must pass otherwise you MUST fix them as we can only proceed to IMPLEMENTED after the whole test suite is 100% passing. - Use your
TodoWritetool to create a task for the Approval Gate - Use your
TodoWritetool to create a task to create thetask_{nr}_completed.mdwith the completion summary after the Approval Gate - Use your
TodoWritetool to create a task to mark the task with[IMPLEMENTED]inside tasks.md file after the Approval Gate
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 · 74 lines · 19 tokens per session scan A 0610ca05188d
execute is a command published in the GitHub repository marcelsud/spec-driven-agentic-development (174 stars, last pushed 9mo ago), licensed MIT. It adds 19 tokens to every session and 1,000 once invoked, about $0.0001 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.
Other commands, from other repositories
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.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.