agentmods.dev

recall

recall is a command for coding agents from atazifor/engineering-memlog. It costs 21 tokens per session (367 once invoked), scanned A, original, MIT.

A workflow for searching an engineering memory log, a store of past technical lessons, and showing the most relevant entries in a readable summary. It can also retrieve the exact prevention rule from a confirmed entry.

In plain words
What is it for?
Use it to search prior engineering incidents or lessons, review matching problems and tags, and read the prevention guidance for a selected entry.
Why use it?
It helps surface earlier solutions and warnings when a problem may have happened before. This can reduce repeated mistakes and keep the relevant lesson tied to the current task.

Command

Part of the engineering-memlog plugin — 1 command, 2 hooks shipped together

not rated 1 2mo ago A scan 21 tokens original MIT
View the source file atazifor/engineering-memlog
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 commands/atazifor/engineering-memlog/recall
Clone the repo
git clone --depth 1 https://github.com/atazifor/engineering-memlog

Or install engineering-memlog, the plugin that ships this one along with the rest of its 1 command, 2 hooks.

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 recall

README.md
[![agentmods](https://agentmods.dev/badge/commands/atazifor/engineering-memlog/recall.svg)](https://agentmods.dev/commands/atazifor/engineering-memlog/recall)
Your own site
<a href="https://agentmods.dev/commands/atazifor/engineering-memlog/recall"><img src="https://agentmods.dev/badge/commands/atazifor/engineering-memlog/recall.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 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 $0.00021 $0.00367
Opus 5 $0.00010 $0.00183
Sonnet 5 $0.00004 $0.00073
Haiku 4.5 $0.00002 $0.00037

Measured 3d ago against content hash 85576fd45da3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

commands/recall.md · 38 lines

What it actually says

You will run a memlog search for the query and read the JSONL output back to the user.

Steps:

  1. Run the memlog search command with the user's query:
~/engineering-memory/bin/memlog search "$ARGUMENTS" --json --limit 10

If $ARGUMENTS is empty, instead run:

~/engineering-memlog/scripts/memlog-context | ~/engineering-memlog/scripts/memlog-shortlist --file ~/engineering-memory/data/entries.jsonl --limit 10

  1. Parse each JSONL line. For every hit, show the user a compact summary:

    • timestamp (date only, YYYY-MM-DD)
    • title
    • one-line excerpt of problem (first ~120 chars)
    • tags (joined with commas)
    • confidence

  2. After the list, ask the user which entry (if any) looks relevant to the current task. If they confirm one, retrieve and read its full prevention field aloud — that's the rule they should apply.

  3. If memlog is not installed or the data file is missing, report that clearly and link to the install instructions in the engineering-memlog README.

Important:

  • Don't dump raw JSON unless the user asks — present a readable summary.
  • Don't paraphrase the prevention rule when reading it back; quote it verbatim. Paraphrasing loses precision.
  • If zero hits, say so and suggest alternate queries (e.g. broader keywords from the user's question).
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. 3d ago First seen · 38 lines · 21 tokens per session scan A 85576fd45da3

Subscribe to this mod's changes

recall is a command published in the GitHub repository atazifor/engineering-memlog (1 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 367 once invoked, about $0.0001 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.

Memory and contextagent-memoryai-agentsai-memoryclaude-codeclaude-code-plugincoding-assistant
Related

Other commands, from other repositories

tree-ring-capture

Capture a concise validated lesson decision warning or preference in Tree Ring Memory.

TerminallyLazy/tree-ring-memory-claude-plugin · 13 tokens

tree-ring-audit

Audit consolidate or forget stale sensitive or superseded Tree Ring Memory entries.

TerminallyLazy/tree-ring-memory-claude-plugin · 13 tokens

tree-ring-dox-sync

Preview and synchronize DOX-style AGENTS.md guidance as source-linked Tree Ring memory.

TerminallyLazy/tree-ring-memory-claude-plugin · 16 tokens

tree-ring-recall

Recall durable Tree Ring Memory context before starting or resuming work.

TerminallyLazy/tree-ring-memory-claude-plugin · 12 tokens

tree-ring-update

Check for or install a verified Tree Ring Memory CLI update without changing installation scope.

TerminallyLazy/tree-ring-memory-claude-plugin · 15 tokens

tree-ring-status

Check receipt-backed Tree Ring harness readiness without claiming configuration is activation.

TerminallyLazy/tree-ring-memory-claude-plugin · 12 tokens