agentmods.dev

research-extract

research-extract is a skill for Claude Code from sunil-goyal-1502/project-memory. It costs 7 tokens per session (744 once invoked), scanned A, original, MIT.

A skill that extracts research findings from the previous coding-agent session transcript, if one was saved.

In plain words
What is it for?
Use it after a new session to review research recorded in .ai-memory/.last-session.txt.
Why use it?
It helps recover useful discoveries such as API behaviour, compatibility details, error causes, performance observations, and workarounds.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the project-memory plugin — 11 skills, 2 agents, 1 MCP server shipped together

not rated 8repo 4mo ago A scan 7 tokens original MIT

Good fit Use it after a new session to review research recorded in .ai-memory/.last-session.txt.

Compare 6 skills from other repositories ↓
View source ↗ sunil-goyal-1502/project-memory
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add sunil-goyal-1502/project-memory
Claude Code
/plugin install project-memory

Made for: Claude Code.

Or install project-memory, the plugin that ships this one along with the rest of its 11 skills, 2 agents, 1 MCP server.

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 research-extract

README.md
[![agentmods](https://agentmods.dev/badge/skills/sunil-goyal-1502/project-memory/research-extract.svg)](https://agentmods.dev/skills/sunil-goyal-1502/project-memory/research-extract)
Your own site
<a href="https://agentmods.dev/skills/sunil-goyal-1502/project-memory/research-extract"><img src="https://agentmods.dev/badge/skills/sunil-goyal-1502/project-memory/research-extract.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 744 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00007 $0.00744
Opus 5 $0.00003 $0.00372
Sonnet 5 $0.00001 $0.00149
Haiku 4.5 $0.00001 $0.00074

Measured 7d ago against content hash 41bf075a3434, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

research-extract 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 7d 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.

skills/research-extract/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract Research from Previous Session

Analyze the condensed transcript from the previous session and extract research findings.

Steps

  1. Check for pending transcript: Read .ai-memory/.last-session.txt.

    • If it doesn't exist or is empty, tell the user: "No previous session transcript found. Research findings are captured from session transcripts saved by the session-end hook."

  2. Read the condensed transcript from .ai-memory/.last-session.txt.

  3. Perform the extraction yourself using these rules:

    Focus on tagged content: Look for lines prefixed with [RESEARCH] (tool calls to WebFetch, WebSearch, or MCP tools) and [RESEARCH-CANDIDATE] (assistant text containing research signals). Also scan untagged content.

    INCLUDE (these ARE research findings):

    • API behavior: response formats, rate limits, edge cases, error codes
    • Library compatibility: version-specific behavior, breaking changes, feature support
    • Error root causes: why errors happen and confirmed fixes
    • Performance findings: measured or observed characteristics
    • Documentation clarifications: corrections to or clarifications of docs
    • Workarounds: solutions to known issues
    • Configuration discoveries: non-obvious settings or requirements

    EXCLUDE (these are NOT research findings):

    • Decisions (architectural choices, conventions, constraints) — those go to decisions.jsonl
    • Implementation steps (code that was written, files created)
    • Transient debugging (print statements, breakpoints)
    • Project-specific code locations
    • Git operations, progress updates

    STALENESS HEURISTIC:

    • Mentions a specific version (e.g., "in React 18", "with Node 20") → "versioned" with version_anchored set
    • Mentions an external service/API (e.g., "GitHub API", "Stripe webhook") → "volatile"
    • Otherwise → "stable"

    DEDUPLICATION:

    • Read existing .ai-memory/research.jsonl first
    • If an extracted finding overlaps with an existing entry (2+ shared tags AND similar topic), skip it unless the new finding is more complete — in that case, set supersedes to the existing entry's id

Read the full file on GitHub · 61 lines

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. 7d ago First seen · 61 lines · 7 tokens per session scan A 41bf075a3434

Subscribe to this mod's changes

research-extract is a skill published in the GitHub repository sunil-goyal-1502/project-memory (8 stars, last pushed 4mo ago), licensed MIT. It adds 7 tokens to every session and 744 once invoked, about $0.0000 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.

Research
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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens