session-distill

session-distill is a skill for Claude Code, Codex from trebormc/drupal-ai-agents. It costs 189 tokens per session (1,648 once invoked), scanned B, original, Apache-2.0.

A way to turn verified lessons from a coding session into lasting instructions for future work. It records useful facts, decisions, and failed approaches so later sessions can avoid repeating the same exploration.

In plain words
What is it for?
Use it after meaningful work to update an existing skill, add project-specific guidance, or create shared instructions based on evidence from the session.
Why use it?
It prevents hard-won fixes and known pitfalls from being forgotten after the session ends.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/trebormc/drupal-ai-agents/session-distill
Any agent
npx skills add trebormc/drupal-ai-agents --skill session-distill
Clone the repo
git clone --depth 1 https://github.com/trebormc/drupal-ai-agents

Made for: Claude Code, Codex.

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 session-distill

README.md
[![agentmods](https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/session-distill.svg)](https://agentmods.dev/skills/trebormc/drupal-ai-agents/session-distill)
Your own site
<a href="https://agentmods.dev/skills/trebormc/drupal-ai-agents/session-distill"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/session-distill.svg" alt="Measured on agentmods" height="20"></a>
Per session 189 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,648 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
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 $0.00189 $0.01648
Opus 5 $0.00095 $0.00824
Sonnet 5 $0.00038 $0.00330
Haiku 4.5 $0.00019 $0.00165

Measured 5d ago against content hash b1024056a8d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

session-distill scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -rli "KEYWORD" ~/.claude/skills/ ~/.claude/rules/ \
.claude/skills/session-distill/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Distill

Turn session learnings into guidance that makes future runs faster and cheaper. The value is NOT documenting what worked — it is documenting the dead ends, so the next agent never walks into them.

Step 1 — Harvest candidates

Mine three sources: the current conversation, LESSONS_LEARNED.md, and Beads task notes (bd show <id> --json for tasks touched this session). A candidate is:

  • A solution that worked AFTER one or more failed attempts (the highest-value kind).
  • A non-obvious environment/API fact that was verified in-session (command output, file read, passing test).
  • A decision between approaches, with the rationale that settled it.

For each candidate, record: problem → attempts that failed and WHY each failed → final solution → root cause → the evidence (the exact command/output or file:line that confirmed it).

Epistemic gate (hard rule): only distill solutions with observed evidence in the session. "The error went away" without a derived cause is not distillable — the fix may have been the cache clear next to it. If the solution was merely the last thing tried, say so and skip it; fossilizing a superstition into permanent guidance poisons every future session. When in doubt, re-verify now (run the command, revert-and-retry) before distilling.

Step 2 — Classify

Tag each candidate on two axes:

  • Failure type — use the taxonomy in the lessons-learned rule (CONFABULATION, ASSUMPTION_ERROR, KNOWLEDGE_GAP, STALE_KNOWLEDGE, ENVIRONMENT_QUIRK).
  • Scope — PROJECT (paths, versions, quirks of THIS codebase: "this theme's build needs X") vs UNIVERSAL (true in any Drupal/DDEV project: "lazy builder args must be scalars").

Step 3 — Route to the right destination

Check for an existing home FIRST — grep the skills/rules for the topic before writing anything new:

# Covers both tools' synced copies plus the project's own skills/rules:
grep -rli "KEYWORD" ~/.claude/skills/ ~/.claude/rules/ \
  ~/.config/opencode/skills/ ~/.config/opencode/rules/ \
  .claude/skills/ .claude/rules/ 2>/dev/null

Read the full file on GitHub · 137 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. 5d ago First seen · 137 lines · 189 tokens per session scan B b1024056a8d3

Subscribe to this mod's changes

session-distill is a skill published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 189 tokens to every session and 1,648 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens