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/merge-work-packets)<a href="https://agentmods.dev/commands/axiomantic/spellbook/merge-work-packets"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/merge-work-packets/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/merge-work-packets"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/merge-work-packets.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 | $0.00019 | $0.02704 |
| Opus 5.5 | $0.00008 | $0.01082 |
| Sonnet 5.5 | $0.00004 | $0.00541 |
| Haiku 4.5 | $0.00002 | $0.00270 |
Grade A, and why
merge-work-packets 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Work Packets
Integrate all completed work packets using merging-worktrees and verify through comprehensive QA gates.
Invariant Principles
- Completeness before integration: ALL tracks must have valid completion markers before ANY merge begins. Partial integration destroys reproducibility.
- Fail fast, fail loud: Stop at first failure. No cascading errors. Clear diagnosis beats silent corruption.
- Evidence over trust: Every claim (track complete, merge clean, tests pass) requires verifiable proof (file exists, commit in history, exit code 0).
- Reversibility: Pre-merge state must be restorable. Integration branch isolates changes until explicit approval.
- Gates are gates: QA gates are mandatory checkpoints, not suggestions. No gate skipping.
Parameters
packet_dir(required): Directory containing manifest.json and completed work packets--continue-merge(optional): Resume at Step 6 after manual conflict resolution
Reasoning Schema
Execution Protocol
Step 1: Load Manifest
manifest_file="$packet_dir/manifest.json"
# Verify manifest exists
if [ ! -f "$manifest_file" ]; then
echo "ERROR: manifest.json not found at $manifest_file"
echo "Ensure packet_dir is correct: $packet_dir"
exit 1
fi
# Load and extract using read_json_safe:
# - feature name
# - tracks list
# - merge_strategy ("merging-worktrees" or "manual")
# - post_merge_qa gates array
# - project_root
Expected manifest fields:
format_version: "1.0.0"feature: Feature being integratedtracks: Array of track metadatamerge_strategy: "merging-worktrees" or "manual"post_merge_qa: Array of QA gate commandsproject_root: Path to main repository
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 · 413 lines · 19 tokens per session scan A 2339a0fa8d23
merge-work-packets is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 2,704 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
worktree
Create a git worktree for isolated feature/fix work.
test-suite
Run comprehensive test suite with coverage analysis.
commit
Stage, commit, and optionally ship further. Pass an escalation token (push, pr, merge, squash, squash merge) to skip the prompt. With no token, commits then asks how far to ship. Delegates message format to the atomic-git-discipline skill.
pr-ready
Run the project's pre-commit review loop to determine whether the current branch is ready to push — lint, tests, parallel pr-review-toolkit agents plus an over-engineering audit, fix-and-re-run until convergence.
clean_gone
Cleans up all git branches marked as [gone] (branches that have been deleted on the remote but still exist locally), including removing associated worktrees.
autotask
Execute development task autonomously from description to PR-ready - handles implementation, testing, and git workflow without supervision.