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/execute-work-packet)<a href="https://agentmods.dev/commands/axiomantic/spellbook/execute-work-packet"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/execute-work-packet.svg" alt="Measured on agentmods" 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 | $0.01977 |
| Opus 5 | $0.00011 | $0.00988 |
| Sonnet 5 | $0.00004 | $0.00395 |
| Haiku 4.5 | $0.00002 | $0.00198 |
Grade A, and why
execute-work-packet scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Work Packet
Invariant Principles
- Dependency-First: Never begin work until all dependent tracks have completion markers
- TDD-Mandatory: Every task follows RED-GREEN-REFACTOR; no implementation without failing test first
- Checkpoint-Resilient: Atomic checkpoints after each task enable fine-grained recovery
- Evidence-Gated: Acceptance criteria verified through fact-checking; claims require proof
- Isolation-Enforced: Worktree branch must match packet specification; no cross-contamination
Parameters
| Parameter | Required | Purpose |
|---|---|---|
packet_path |
Yes | Absolute path to work packet .md file |
--resume |
No | Resume from existing checkpoint |
Execution States
[Parse] -> [Dependencies] -> [Checkpoint?] -> [Worktree] -> [TDD Loop] -> [Complete]
| |
v v
[Wait/Abort] [Fail/Stop]
Phase 1: Parse and Validate Packet
packet_file="<packet_path>"
packet_dir="$(dirname "$packet_file")"
# Extract via parse_packet_file: format_version, feature, track, worktree, branch, tasks
# Load manifest: $packet_dir/manifest.json (dependency graph)
Extracted fields: format_version, feature, track, worktree, branch, tasks (list of {id, description, files, acceptance}).
Parse failure: If packet file is missing or malformed, HALT with error. Do not proceed.
Phase 2: Dependency 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.
- 4d ago First seen · 264 lines · 22 tokens per session scan A 843aa9cc2173
execute-work-packet is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 1,977 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 2026-09-03.
Other commands, from other repositories
implement-approved-slice
Implement only the approved slice with minimal, explicit, review-friendly changes, then persist execution evidence in slice notes and TASKSTATE.md. The single official execution path of the workflow. Supports an opt-in test-first (TDD) mode, enabled per slice or via --tdd, that writes the failing test before the code…
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.
report-issue-with-atomic
Open an issue against the atomic-claude repo itself (bugs/feature requests with the installed config, not the user's current project).
report-issue
Open a atomic GitHub issue via gh. Bug report or feature request — auto-detect from user's description.
forge
/forge Full Forge pipeline (semi-auto + parallel) /forge [prd-file] Forge a specific PRD /forge --blitz Forge with TDD enforcement.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.