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/visactor/vchart/speckit.autogit clone --depth 1 https://github.com/VisActor/VChartWhat 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 | $0.00031 | $0.01042 |
| Opus 5 | $0.00015 | $0.00521 |
| Sonnet 5 | $0.00006 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
speckit.auto 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
Outline
This command orchestrates the full Spec-Driven Development (SDD) lifecycle, executing each of the four core phases in a strict, sequential, and non-interactive manner. It ensures that each phase completes before the next one begins, mirroring the exact semantics of executing each /speckit.* command individually.
Execution is strictly sequential. Parallel execution of phases is prohibited.
Pre-flight Check
- Validate User Input:
- If
$ARGUMENTSis empty, the process will halt with an error. The initial feature description is mandatory to start thespecifyphase.
- If
Phase 1: Specify (/speckit.specify)
- Action: The workflow begins by invoking
/speckit.specifywith the provided$ARGUMENTS. This is the single entry point for user input. - Process: This phase will automatically generate a feature branch, create the
spec.mdfile, and run all associated validation and checklist generation steps as defined in thespeckit.specifycommand. - Handoff: Upon successful completion, it will automatically trigger the
planphase. - Output Report:
- "Phase 1 (Specify) completed."
BRANCH_NAME: [The generated feature branch name]SPEC_FILE: [Path to the generated spec.md file]
Phase 2: Plan (/speckit.plan)
- Action: Triggered automatically after
specifycompletes. It requires no additional arguments and operates on the context established by the previous phase. - Process: This phase will generate the
plan.mdand all its associated design artifacts (e.g.,research.md,data-model.md,contracts/). It strictly follows the "Phase 0" and "Phase 1" steps outlined in thespeckit.plancommand. - Handoff: Upon successful completion, it will automatically trigger the
tasksphase. - Output Report:
- "Phase 2 (Plan) completed."
IMPL_PLAN: [Path to the generated plan.md file]DERIVED_ARTIFACTS: [List of paths to other generated files like research.md]
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 · 68 lines · 0 tokens per session scan A 2420bb0e1294
speckit.auto is a command published in the GitHub repository VisActor/VChart (1,834 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 1,042 once invoked, about $0.0002 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
guide
Every method on App should have its own unit tests.
lattice-cycle
Run one Lattice work cycle — pull the next runnable tasks, dispatch the agent team, verify, commit, push, and advance the queue.
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.