agentmods.dev

distil-certify

distil-certify is a command for Claude Code from dshakes/distil. It costs 13 tokens per session (249 once invoked), scanned A, original, no licence file.

A command that creates a certificate for an agent's task trajectory, estimating how many otherwise solvable tasks compression might make fail.

In plain words
What is it for?
It is for certifying the possible task cost of compression over an agent trajectory.
Why use it?
It gives a bounded risk estimate for using context compression across a sequence of agent actions.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the distil plugin — 1 skill, 8 commands shipped together

not rated 21repo +1 yesterday A scan 13 tokens custom licence

Good fit It is for certifying the possible task cost of compression over an agent trajectory.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/dshakes/distil/distil-certify
View source ↗ dshakes/distil dshakes.github.io
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/dshakes/distil

Made for: Claude Code.

Or install distil, the plugin that ships this one along with the rest of its 1 skill, 8 commands.

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 distil-certify

README.md
[![agentmods](https://agentmods.dev/badge/commands/dshakes/distil/distil-certify/github.svg)](https://agentmods.dev/commands/dshakes/distil/distil-certify)
Your own site
<a href="https://agentmods.dev/commands/dshakes/distil/distil-certify"><img src="https://agentmods.dev/badge/commands/dshakes/distil/distil-certify/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 distil-certify

Your own site · 80×15
<a href="https://agentmods.dev/commands/dshakes/distil/distil-certify"><img src="https://agentmods.dev/badge/commands/dshakes/distil/distil-certify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 249 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 unknown 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 $0.00013 $0.00249
Opus 5.5 $0.00005 $0.00100
Sonnet 5.5 $0.00003 $0.00050
Haiku 4.5 $0.00001 $0.00025

Measured 2mo ago against content hash bc7061aad87e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

distil-certify 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 2mo 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.

plugins/distil/commands/distil-certify.md · 23 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 2mo ago First seen · 23 lines · 13 tokens per session scan A bc7061aad87e

Subscribe to this mod's changes

distil-certify is a command published in the GitHub repository dshakes/distil (21 stars, last pushed yesterday), with no licence file. It adds 13 tokens to every session and 249 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 2026-08-30.

Analytics and metricsBuilding agentsCost OptimizationLLMagentsai-infrastructureanthropiccontext-compression
Related

distil-certify compared with commands from other repositories

distil-certify next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
distil-certifydshakes/distilCommand21yesterdaynoneA13Claude Code
feature-devbearlike/AssistantCommand437d agoMITA11Claude Code
revise-claude-mdbearlike/AssistantCommand437d agoMITA11Claude Code
code-reviewbearlike/AssistantCommand437d agoMITA5Claude Code
carefulyonatangross/orchestkitCommand299yesterdayMITC84Claude Code, Cursor
roadmap-edit.templateevan043/claude-cli-advanced-starter-packCommand613mo agoMITA0Claude Code
vdb-scan.templateevan043/claude-cli-advanced-starter-packCommand613mo agoMITA0Claude Code