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.
npx agentmods add commands/axiomantic/spellbook/address-pr-feedbackgit 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/address-pr-feedback)<a href="https://agentmods.dev/commands/axiomantic/spellbook/address-pr-feedback"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/address-pr-feedback.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 | $0.00043 | $0.04386 |
| Opus 5 | $0.00022 | $0.02193 |
| Sonnet 5 | $0.00009 | $0.00877 |
| Haiku 4.5 | $0.00004 | $0.00439 |
Grade A, and why
address-pr-feedback 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 6d 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 — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<CRITICAL_INSTRUCTION> This command analyzes PR review feedback and helps address each comment. Take a deep breath. This is very important to my career.
You MUST:
- NEVER post or commit anything without explicit user approval via AskUserQuestion
- Analyze ALL unresolved comment threads
- Categorize each as: acknowledged, silently fixed, or unaddressed
- Guide user through fixing unaddressed items step-by-step
This is NOT optional. This is NOT negotiable. User approval is required for every action. </CRITICAL_INSTRUCTION>
Invariant Principles
- User Approval Required: NEVER post or commit without explicit AskUserQuestion approval. This is NOT negotiable.
- Total Coverage: Every unresolved thread MUST be categorized. No comment left behind.
- Evidence-Based Claims: "Fixed" claims require commit hash + verification. No assumptions.
- Interactive-First: Guide user through decisions step-by-step. Safe to run.
- Audit Trail: Log all actions to
$SPELLBOOK_CONFIG_DIR/logs/.
<BEFORE_RESPONDING> Before analyzing ANY PR:
- Do I have the PR number/URL?
- Have I determined the code state to examine (local vs remote)?
- Have I fetched ALL review comment threads?
- Have I categorized each thread correctly?
Now proceed with the analysis. </BEFORE_RESPONDING>
Address PR Feedback
Interactive wizard to analyze and address PR review feedback.
Usage
/address-pr-feedback [pr-number|pr-url] [--reviewer=username] [--non-interactive]
Arguments
pr-number|pr-url: Optional. PR number (e.g., 9224) or full GitHub URL--reviewer=username: Optional. Filter comments by specific reviewer (e.g.,--reviewer=johndoe)--non-interactive: Optional. Show analysis report only, skip the wizard
Core Algorithm
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.
- 6d ago First seen · 624 lines · 43 tokens per session scan A e102c6ca84f3
address-pr-feedback is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 2d ago), licensed MIT. It adds 43 tokens to every session and 4,386 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 2026-08-31.
Other commands, from other repositories
mr-description-creator
Generate and apply MR/PR description directly via gh or glab CLI (project).
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.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
undo-commit
Soft-undo the last commit. Restores its changes as staged, leaves working tree intact. Refuses if HEAD is already pushed to a tracked remote.
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.
done
Finish a task - document, create PR or merge, close.