pr-distill-bless

pr-distill-bless is a command for Claude Code from axiomantic/spellbook. It costs 17 tokens per session (601 once invoked), scanned A, original, MIT.

A command for adding a named, validated pattern to the list used by pull-request distillation. A blessed pattern becomes available to future distillation runs in the project.

In plain words
What is it for?
Use it to save patterns such as import cleanups or test-factory setup for future pull-request analysis.
Why use it?
It prevents useful review patterns from being lost and requires confirmation before adding or replacing one.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to save patterns such as import cleanups or test-factory setup for future pull-request analysis.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/pr-distill-bless
Install

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.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Made for: Claude Code.

Wrote 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.

agentmods badge for pr-distill-bless

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/pr-distill-bless/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/pr-distill-bless)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/pr-distill-bless"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/pr-distill-bless/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.

agentmods 80×15 button for pr-distill-bless

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/pr-distill-bless"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/pr-distill-bless.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 601 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00601
Opus 5 $0.00009 $0.00300
Sonnet 5 $0.00003 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured 6d ago against content hash ed280e203991, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pr-distill-bless 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.

commands/pr-distill-bless.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Distill Bless

Invariant Principles

  1. User Confirmation Required: Never bless patterns automatically. User must explicitly invoke this command.
  2. Validate Pattern ID: Pattern must match validation rules (lowercase, hyphens, 2-50 chars).
  3. Warn on Overwrite: If pattern already exists, warn and confirm before updating.
  4. Persistence Is Immediate: Once blessed, pattern affects all future distillations in this project.

Execution

Usage

/distilling-prs-bless <pattern-id>

Examples

/distilling-prs-bless query-count-json
/distilling-prs-bless import-cleanup
/distilling-prs-bless test-factory-setup

Pattern ID Rules

Requirement Valid Invalid
Length 2-50 chars a, very-long-pattern-id-...
Characters [a-z0-9-] CAPS, under_score
Start Letter 123-foo
End Letter or number foo-
No double hyphen foo-bar foo--bar

Reserved prefix: _builtin- (built-in patterns only)

Configuration

Blessed patterns stored in: ~/.local/spellbook/docs/<project-encoded>/distilling-prs-config.json

{
  "blessed_patterns": ["query-count-json", "import-cleanup"]
}

Notes

  • Pattern IDs come from "Discovered Patterns" section of distillation reports
  • To remove a blessed pattern, manually edit the config file

Read the full file on GitHub · 88 lines

Changes

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.

  1. 6d ago First seen · 88 lines · 17 tokens per session scan A ed280e203991

Subscribe to this mod's changes

pr-distill-bless is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 601 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.