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/johnreitano/spekka/create-specgit clone --depth 1 https://github.com/johnreitano/spekkaWhat 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 | $0.00500 |
| Opus 5 | $0.00000 | $0.00250 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
create-spec 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 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.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Creation Process
You are helping me create a complete specification for a new feature. This combines the spec shaping and spec writing processes into one seamless workflow.
This process will follow 4 main phases, each with their own workflow steps:
Process overview (details to follow)
PHASE 1. Initialize spec PHASE 2. Research requirements for this spec PHASE 3. Write the specification document PHASE 4. Inform the user that the spec is complete
Follow each of these phases and their individual workflows IN SEQUENCE:
Multi-Phase Process:
PHASE 1: Initialize Spec
Use the spec-initializer subagent to initialize a new spec.
IF the user has provided a description, provide that to the spec-initializer.
The spec-initializer will provide the path to the dated spec folder (YYYY-MM-DD-spec-name) they've created.
PHASE 2: Research Requirements
After spec-initializer completes, immediately use the spec-shaper subagent:
Provide the spec-shaper with:
- The spec folder path from spec-initializer
The spec-shaper will give you several separate responses that you MUST show to the user. These include:
- Numbered clarifying questions along with a request for visual assets (show these to user, wait for user's response)
- Follow-up questions if needed (based on user's answers and provided visuals)
IMPORTANT:
- Display these questions to the user and wait for their response
- The spec-shaper may ask you to relay follow-up questions that you must present to user
PHASE 3: Write Specification Document
After requirements gathering is complete, use the spec-writer subagent to create the specification document:
Provide the spec-writer with:
- The spec folder path from Phase 1
- The requirements from
planning/requirements.md - Any visual assets in
planning/visuals/
The spec-writer will create spec.md inside the spec folder.
PHASE 4: Inform the User
After all steps complete, inform the user:
Spec creation is complete!
✅ Spec folder created: `[spec-path]`
✅ Requirements gathered
✅ Visual assets: [Found X files / No files provided]
✅ Spec document created: `[spec-path]/spec.md`
NEXT STEP 👉 Run `/spekka:create-tasks` to generate your tasks list for this spec.
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 · 66 lines · 0 tokens per session scan A e8a025ab5f14
create-spec is a command published in the GitHub repository johnreitano/spekka (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 500 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
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.
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.