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.
git clone --depth 1 https://github.com/ErebusEnigma/context-memoryWrote 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/commands/erebusenigma/context-memory/recall)<a href="https://agentmods.dev/commands/erebusenigma/context-memory/recall"><img src="https://agentmods.dev/badge/commands/erebusenigma/context-memory/recall/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/commands/erebusenigma/context-memory/recall"><img src="https://agentmods.dev/badge/commands/erebusenigma/context-memory/recall.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 | $0.00007 | $0.00859 |
| Opus 5.5 | $0.00003 | $0.00344 |
| Sonnet 5.5 | $0.00001 | $0.00172 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/recall Command
Search past sessions stored in context memory.
Usage
/recall <query> [options]
Arguments:
query(required): Search terms to find relevant sessions
Options:
--project: Limit search to current project only--detailed: Include full message content and code snippets--limit N: Maximum number of results (default: 10)--format: Output format:jsonormarkdown(default: markdown)
Examples
/recall authentication
/recall "database migration" --project
/recall jwt --detailed --limit 5
/recall "error handling" --project --detailed
Workflow
When the user runs /recall:
-
Parse Query and Options
Extract the search query and any flags:
--project-> filter by current project path--detailed-> include tier 2 content--limit N-> cap results
-
Execute Search
Run the search script:
python "~/.claude/skills/context-memory/scripts/db_search.py" "<query>" [--project "$(pwd)"] [--detailed] [--limit N] --format markdown -
Present Results
Display results in a clear, scannable format:
# Context Memory Results **Query**: "authentication" **Results**: 3 sessions --- ## 1. 2026-01-15 | my-app (Match #1) **Summary**: Implemented JWT auth with refresh token rotation **Topics**: authentication, JWT, security, Node.js **Decisions**: - Use RS256 for token signing - 15-minute access token expiry <details><summary>Full Context</summary> [Detailed content when --detailed flag is used] </details> -
Offer Follow-up Actions
If results are helpful, offer to:
- Show more details for a specific session
- Apply learnings from a past session to current work
- Search with different terms
If results are insufficient:
- Suggest broader search terms
- Offer to search in messages (deeper search)
- Suggest removing
--projectfilter
Search Tips
The search uses FTS5 full-text search with Porter stemming:
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 · 139 lines · 7 tokens per session scan A d5f8ee4767ff
recall is a command published in the GitHub repository ErebusEnigma/context-memory (7 stars, last pushed 8mo ago), licensed MIT. It adds 7 tokens to every session and 859 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
resume
Resume work from .claude/handoff/current.md in this fresh session (skip --resume).
save
Save a compact handoff checkpoint so a fresh session can resume cheaply (no --resume).
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.
resume
Show the restored Continuity project state (frozen constraints, decisions, rejected paths, next step).