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.
git clone --depth 1 https://github.com/axiomantic/spellbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/axiomantic/spellbook/feature-implement-execute)<a href="https://agentmods.dev/commands/axiomantic/spellbook/feature-implement-execute"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-implement-execute/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/axiomantic/spellbook/feature-implement-execute"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-implement-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00022 | $0.11056 |
| Opus 5.5 | $0.00009 | $0.04422 |
| Sonnet 5.5 | $0.00004 | $0.02211 |
| Haiku 4.5 | $0.00002 | $0.01106 |
Grade A, and why
feature-implement-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 1mo 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 — 1,200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Execution (/feature-implement-execute)
Phase 4 of the develop workflow. Run after /feature-implement completes
(Phase 3 planning approved; for large delegated runs, the 3.4.7 one-pager
approved).
Do NOT begin Phase 4 until the "STOP AND VERIFY: Phase 3 → Phase 4 Transition"
checklist at the end of /feature-implement passes IN FULL. If ANY item is
unchecked: STOP and return to /feature-implement.
On the zero-flag fast path, the user-confirmed inline plan (<=5 steps) stands in for the Phase 3 artifacts; every other Phase 4 gate below still runs.
Anti-rationalization: "the plan is small" / "the gates are overkill here" = Pattern 3 (Time Pressure) or Pattern 5 (Competence Assertion). The review floor is never zero.
Invariant Principles
- Design precedes implementation - Never implement without an approved design document and implementation plan
- Delegate actual work - Main context orchestrates; subagents write code, run tests, perform reviews
- Quality gates are mandatory - Code review, fact-checking, and green mirage audit after every task; no exceptions
- Behavior preservation in refactoring - Test verification at every transformation; no behavior changes without approval
- No batch exemption - A batched or multi-task dispatch exempts NOTHING: every task the batch covers passes the per-task gates 4.4, 4.5, and 4.5.1 individually before it may be marked complete. Batch size never substitutes for per-task gating.
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.
- 1mo ago First seen · 1,200 lines · 22 tokens per session scan A da6dc053e2ac
feature-implement-execute is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 11,056 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
tdd
A command for test-driven development, a method where you write a failing test first, then code to pass it, and finally improve the code.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
speckit.tdd.plan
Derive the feature's test list by delegating to zfa tdd plan (deterministic engine); falls back to LLM-guided derivation only when zfa is unavailable.
speckit.tdd.verify
Audit TDD discipline by delegating to zfa tdd verify (mutation testing, evidence integrity); the LLM interprets the verdict and drives remediation.
speckit.spec-stats.not-green
On-demand view of specs whose latest test evidence is red or unknown, with the exact evidence line quoted from tdd/cycle-log.md and the command that would produce evidence.