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-design)<a href="https://agentmods.dev/commands/axiomantic/spellbook/feature-design"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-design/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-design"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/feature-design.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 | $0.00011 | $0.03792 |
| Opus 5 | $0.00005 | $0.01896 |
| Sonnet 5 | $0.00002 | $0.00758 |
| Haiku 4.5 | $0.00001 | $0.00379 |
Grade A, and why
feature-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature-design
Phase 2 of the develop workflow. Run after /feature-discover completes.
Before ANY Phase 2 work, run this check:
PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
PROJECT_ENCODED=$(echo "$PROJECT_ROOT" | sed 's|^/||' | tr '/' '-')
echo "=== Phase 2 Prerequisites ==="
# CHECK 1: needs_design must be set (this phase does not run otherwise)
echo "Required: needs_design == true"
echo "Current need-flags: [SESSION_PREFERENCES.need_flags]"
# needs_infrastructure IMPLIES needs_design (auto-set in Phase 0; see design §2.2).
# If needs_design is not set, this phase does not run — return to the orchestrator.
# CHECK 2: Understanding document must exist (Phase 1.5 artifact)
echo "Required: Understanding document exists"
ls ~/.local/spellbook/docs/$PROJECT_ENCODED/understanding/ 2>/dev/null || echo "FAIL: No understanding document found"
# CHECK 3: Completeness score must be 100%
echo "Required: Phase 1.5 completeness score = 100%"
echo "Verify: SESSION_CONTEXT.design_context populated with no TBD values"
# CHECK 4: Devil's advocate was dispatched
echo "Required: Devil's advocate review completed"
If ANY check fails: STOP. Return to the appropriate phase.
Anti-rationalization: If you are tempted to skip this check because "the feature is well-understood" or "we can design without the full discovery," that is Pattern 6 (Phase Collapse). The understanding document IS the input to design. Without it, design is guesswork.
Invariant Principles
- Discovery precedes design - Design only after
design_contextis fully populated; never design without research findings - Synthesis mode for subagents - Design-exploration subagent receives complete context; no interactive discovery in design phase
- Review is mandatory - Every design document must pass
reviewing-design-docsbefore proceeding - Approval gates respect mode - Interactive mode pauses for user; autonomous mode auto-fixes all findings
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.
- 5d ago First seen · 392 lines · 11 tokens per session scan A 1a0ccaab4d3a
feature-design is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 3,792 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
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.
add-command
Add a new slash command to the current plugin.