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 skills add ychampion/cskill-agents --skill forked-auto-memory-extractiongit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/skills/ychampion/cskill-agents/forked-auto-memory-extraction)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/forked-auto-memory-extraction"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/forked-auto-memory-extraction/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.
<a href="https://agentmods.dev/skills/ychampion/cskill-agents/forked-auto-memory-extraction"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/forked-auto-memory-extraction.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00029 | $0.00423 |
| Opus 5.5 | $0.00012 | $0.00169 |
| Sonnet 5.5 | $0.00006 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
forked-auto-memory-extraction 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 1mo 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Forked Auto Memory Extraction
Domain: background-extraction Trigger: Use whenever memory harvesting must run in a background agent after the main turn completes so the main prompt stays responsive. Source Pattern: Distilled from reviewed background memory extraction and forked-agent isolation implementations.
Core Method
Spawn a forked memory-extraction agent after the parent turn finishes so the main session can stay responsive. Give the fork enough inherited context to understand the completed turn, but restrict its tools to a fenced set of read operations plus tightly scoped writes into the memory directory. The fork should save memories only when the main agent did not already persist the same content. This moves memory harvesting off the hot path without letting the background agent roam the rest of the workspace.
Key Rules
- Build the extraction prompt from stable inherited turn context so the forked agent sees the same facts without mutating the main conversation.
- Fork children may only write into the memory directory and must not interact with the main conversation directly.
- Persist memories only when the main agent did not already save the same content; otherwise skip to avoid duplicates and race conditions.
- Treat the forked agent as fenced: read-only everywhere else, controlled writes only for the memory path.
Example Application
When the user’s turn finishes with memory-worthy insights, dispatch this skill: the forked agent copies the last assistant message, runs the extraction prompt, and writes structured entries into memory/*.md while the parent stays in the REPL and accepts the next user question.
Anti-Patterns (What NOT to do)
- Don’t run the extraction inside the main agent while it’s still processing the turn; that delays responses and can hit prompt budgets.
- Don’t let the forked agent use unrestricted shells or write outside the memory directory; keep it fenced to avoid privilege escalation or accidental file 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.
- 1mo ago First seen · 29 lines · 29 tokens per session scan A c2969df046fe
forked-auto-memory-extraction is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 423 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 2026-09-03.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
brain-bootstrap
Seed a freshly-scaffolded brain with real project knowledge — on an existing (brownfield) project read the code, docs, and git log, then draft only the root pages that have meaningful content and capture key historical decisions; on a near-empty (greenfield) project interview the user. Every write goes through the…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.