context-digest

context-digest is a skill for Claude Code, Codex from sam-ueckert/oc-memory. It costs 70 tokens per session (942 once invoked), scanned A, original, MIT.

A script and setup pattern that keeps a short digest of important stored memories in the agent's startup context file. It supports OpenClaw's MEMORY.md and Claude Code's CLAUDE.md.

In plain words
What is it for?
Use it to refresh high-priority memories automatically every few hours or when a new coding workspace starts.
Why use it?
It saves the agent from manually searching memory at the start of each session.

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/sam-ueckert/oc-memory/context-digest
Any agent
npx skills add sam-ueckert/oc-memory --skill context-digest
Clone the repo
git clone --depth 1 https://github.com/sam-ueckert/oc-memory

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 context-digest

README.md
[![agentmods](https://agentmods.dev/badge/skills/sam-ueckert/oc-memory/context-digest.svg)](https://agentmods.dev/skills/sam-ueckert/oc-memory/context-digest)
Your own site
<a href="https://agentmods.dev/skills/sam-ueckert/oc-memory/context-digest"><img src="https://agentmods.dev/badge/skills/sam-ueckert/oc-memory/context-digest.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 942 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00070 $0.00942
Opus 5 $0.00035 $0.00471
Sonnet 5 $0.00014 $0.00188
Haiku 4.5 $0.00007 $0.00094

Measured 4d ago against content hash ea15dda1d54b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-digest 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/gen-context-digest.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/context-digest/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Digest

Keeps a ## Memory Digest section in your agent's context file fresh so every new session starts with high-salience memories already loaded — no manual search needed.

Works with OpenClaw (MEMORY.md), Claude Code (CLAUDE.md), and any agent platform that auto-injects a project file at session start.

How It Works

  1. A cron job (or manual run) executes gen-context-digest.sh every 2-3 hours
  2. The script queries mem scene <name> for each configured scene, filters by salience ≥ 0.8, and rewrites a bounded block in the target file
  3. Your agent platform auto-injects the file at session start → digest is in context before the first user message

Target File Auto-Detection

The script picks the target file in this order:

  1. Explicit argument: bash gen-context-digest.sh /path/to/file.md
  2. MEMORY.md in $WORKSPACE (OpenClaw convention)
  3. CLAUDE.md in $WORKSPACE (Claude Code convention)
  4. Falls back to $WORKSPACE/MEMORY.md (creates on first cron run)

Setup

1. Copy the script

cp skills/context-digest/scripts/gen-context-digest.sh ~/bin/gen-context-digest.sh
chmod +x ~/bin/gen-context-digest.sh

2. Test it

WORKSPACE=/path/to/your/workspace bash ~/bin/gen-context-digest.sh

Verify the ## Memory Digest block appears in your target file.

3. Add HTML markers to your target file

Add this block where you want the digest to appear:

<!-- ARCHY_DIGEST_START -->
<!-- ARCHY_DIGEST_END -->

The script will replace between the markers on next run. If no markers exist, it appends to the end of the file.

4. Install cron

crontab -e

Add (adjust paths):

0 */3 * * * export PATH="$HOME/bin:/usr/local/bin:/usr/bin:/bin:$PATH"; WORKSPACE=/path/to/workspace bash ~/bin/gen-context-digest.sh >> /tmp/context-digest.log 2>&1

Platform-Specific Notes

OpenClaw

OpenClaw auto-injects MEMORY.md at session start. Add the markers to MEMORY.md and the digest is available before the first user message.

Read the full file on GitHub · 120 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 120 lines · 70 tokens per session scan A ea15dda1d54b

Subscribe to this mod's changes

context-digest is a skill published in the GitHub repository sam-ueckert/oc-memory (2 stars, last pushed 21d ago), licensed MIT. It adds 70 tokens to every session and 942 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

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

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 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