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/writing-commands-paired)<a href="https://agentmods.dev/commands/axiomantic/spellbook/writing-commands-paired"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/writing-commands-paired/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/writing-commands-paired"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/writing-commands-paired.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 | $0.00033 | $0.00776 |
| Opus 5 | $0.00016 | $0.00388 |
| Sonnet 5 | $0.00007 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
writing-commands-paired 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 7d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MISSION
When a command creates artifacts (files, injections, manifests), create a paired removal command with proper contracts for manifest tracking, discovery, safety, and verification.
Invariant Principles
- Paired commands share a contract: If command A creates artifacts, command B must know how to find and remove them. The manifest is the interface.
- Commands are direct prompts: Load entirely into context. No subagent dispatch. The agent reads and executes.
- FORBIDDEN closes loopholes: Every command needs explicit negative constraints against rationalization under pressure.
Paired Command Protocol
Contract requirements:
| Requirement | Responsibility |
|---|---|
| Manifest | Creating command writes to a known location (JSON recommended) |
| Discovery | Removing command reads manifest; falls back to heuristic search if missing |
| Safety | Removing command checks for user modifications before reverting |
| Verification | Both commands verify their work compiled/resolved correctly |
Naming: <name> and <name>-remove (e.g., test-bar / test-bar-remove)
Cross-references (required in both commands):
| Command | Must include |
|---|---|
| Creating | "To remove: /command-name-remove" |
| Removing | "Removes artifacts from /command-name" |
Steps
- Identify all artifacts the creating command produces (files, config changes, injections)
- Define manifest format and location (JSON recommended, stored alongside artifacts)
- Write the creating command with manifest generation baked into its protocol
- Write the removal command that:
- Reads the manifest first
- Falls back to heuristic search if manifest missing
- Checks modification timestamps before reverting
- Reports what was removed and what was preserved
- Add cross-references in both commands
- Test both commands: create then remove, verify clean state
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.
- 7d ago First seen · 82 lines · 33 tokens per session scan A 4a3fd078a50a
writing-commands-paired is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 776 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 2026-09-03.
Other commands, from other repositories
subagent-implementation
Orchestrate implement→review subagent loop until task complete. Reads the approved spec, writes a thin brief to .claude/.scratchpad/, dispatches fresh-context subagents, loops until reviewer signs off, commits per green iteration, then updates repo docs.
documentation
Bootstrap and maintain project documentation surfaces. Two modes: bootstrap (discover doc files, index them in CLAUDE.md) and authoring (scan for unindexed docs, match diff against indexed surfaces, walk stale/incomplete/missing items with Yes/Later/Remind/Skip).
watch-ci
Spawn a background Haiku-backed subagent to watch CI for the current branch (or specified target). Provider-agnostic — the subagent inspects project signals to identify the CI system (GitHub Actions, GitLab CI, CircleCI, etc.) and picks the right CLI. Returns immediately; reports back when CI reaches a terminal state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
integrate
Analyze and enhance AI artifacts to leverage Subcog memory effectively.
maintain
Run automated maintenance — seeker finds bugs from pod logs and raises GitHub issues, fixer picks them up and creates PRs. Can run as a one-shot or scheduled via /schedule.