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 skills/stefaniuk/loadout/speckit-implementnpx skills add stefaniuk/loadout --skill speckit-implementgit clone --depth 1 https://github.com/stefaniuk/loadoutWhat 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 | $0.00020 | $0.03759 |
| Opus 5 | $0.00010 | $0.01879 |
| Sonnet 5 | $0.00004 | $0.00752 |
| Haiku 4.5 | $0.00002 | $0.00376 |
Grade A, and why
speckit-implement 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.
This is a copy
77% identical to speckit-implement — 164 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Mode Guard
Use this skill only when the active local workflow mode is speckit.
Before proceeding:
- Run
./scripts/hooks/workflow-mode.sh status. - If the active mode is
superpowers, stop and tell the user to switch withmake workflow-use mode=speckitor continue with the Superpowers workflow instead. - Do not mix
speckit-*commands with Superpowers workflow skills in the same session or worktree.
You MUST adhere to the following mandatory requirements when implementing features.
Workflow context:
- Input:
tasks.md(actionable task list) - Output: Working code with passing tests
- Verification: Execute Show & Tell steps after each phase
Base requirements: Follow all rules in copilot-instructions.md, particularly:
- Repository tooling
- Test-driven development
- Repository verification policy
Prerequisite: This skill assumes tasks.md already exists. If tasks.md does not exist, stop and tell the user to run /speckit-tasks first.
Scope Notes
- For infrastructure, scripts, documentation, or reporting tools, use lightweight validation that stays explicit and deterministic
- If project setup or ignore-file guidance does not apply to the feature scope, skip that work instead of inventing application-style setup tasks
Implementation Process (Mandatory)
- Work through tasks in
tasks.mdsequentially - For code tasks, follow TDD: write failing test first, then implement, then refactor
- After completing each phase or user story, execute its
Show & Tellsteps to verify correctness - For infrastructure, scripts, documentation, or reporting tools, lightweight validation such as file presence, expected keys, or deterministic command output is sufficient
- Respect the repository's canonical local quality-gate policy after every source code change; where hooks enforce the gates automatically, do not duplicate the same gate commands manually unless diagnosing a failure
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 · 278 lines · 20 tokens per session scan A 64fecee332fb
speckit-implement is a skill published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 4d ago), licensed MIT. It adds 20 tokens to every session and 3,759 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 77% identical to speckit-implement, differing in 164 lines, and is treated as a copy.
Other skills, from other repositories
sddp-autopilot
Run the full SDD feature-delivery pipeline. Direct command-bar dispatch only; do not select for general queries.
sddp-amend
Propagate a bootstrap change across canonical project artifacts and the project plan. Direct command-bar dispatch only; do not select for general queries.
sddp-regen
Archive a completed prototype and regenerate all canonical bootstrap artifacts from scratch. Direct command-bar dispatch only; do not select for general queries.
sddp-checklist
Generate and evaluate a requirements quality checklist. Direct command-bar dispatch only; do not select for general queries.
sddp-clarify
Reduce ambiguity in the current feature specification. Direct command-bar dispatch only; do not select for general queries.
sddp-devops
Create or refine the deployment and operations document. Direct command-bar dispatch only; do not select for general queries.