recall

A context lookup skill for answering questions about an existing project's structure, architecture, decisions, and behaviour.

In plain words
What is it for?
Use it to explain how a project works, why it was designed a certain way, or where its conventions and trade-offs come from.
Why use it?
It helps an agent find and use existing research and planning documents before exploring the codebase directly.

Skill for Claude CodeCodex

Part of the smith plugin — 2 skills, 8 commands, 6 agents shipped together

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/brettbuddin/claude-plugins/recall
Any agent
npx skills add brettbuddin/claude-plugins --skill recall
Clone the repo
git clone --depth 1 https://github.com/brettbuddin/claude-plugins

Made for: Claude Code, Codex.

Or install smith, the plugin that ships this one along with the rest of its 2 skills, 8 commands, 6 agents.

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 469 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 $0.00102 $0.00469
Opus 5 $0.00051 $0.00234
Sonnet 5 $0.00020 $0.00094
Haiku 4.5 $0.00010 $0.00047

Measured 3d ago against content hash d35c8644e679, 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.

smith/skills/recall/SKILL.md · 38 lines

What it actually says

Context Lookup

This skill scopes context collection to existing Smith research and plan documents before falling back to direct codebase exploration.

When This Skill Applies

This skill activates for general questions about the project: architecture, design rationale, how something works, conventions, or trade-offs. It does not apply when the user is running a Smith pipeline Command or requesting code changes.

Procedure

1. Resolve Output Directory

Check for a .smith.local.yaml file in the project root. If it exists, read the output_directory value. If absent, default to docs/. Use this as the base for all document paths below.

2. Check for Existing Documents

Glob for files in these directories (relative to the working directory):

  • <output_directory>/research/*.md
  • <output_directory>/plans/*.md

If no files exist in either directory, skip to step 4.

3. Select and Read Relevant Documents

Prefer documents already known to the current conversation (i.e., files read or produced earlier in this session). Among remaining candidates, prefer the most recently modified files. If there is exactly one file whose topic matches the question, use it. If there are multiple plausible matches and the best choice is ambiguous, stop and ask the user which document to consult before proceeding.

Read the selected document(s). If the answer is fully covered by the existing documents, respond directly from them. Cite the source file path when drawing from a specific document.

4. Fall Back to Exploration

If no existing documents are relevant, or they do not fully answer the question, proceed with normal codebase exploration (Glob, Grep, Read, or the Explore agent as appropriate). Do not re-research topics already covered by an existing document.

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 · 102 tokens per session scan A d35c8644e679

Subscribe to this mod's changes

recall is a skill published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 102 tokens to every session and 469 once invoked, about $0.0005 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens