recover-context

recover-context is a skill for Claude Code, Codex from pchalasani/claude-code-tools. It costs 36 tokens per session (489 once invoked), scanned A, original, MIT.

A workflow for recovering the last task and relevant files from an earlier coding-agent session.

In plain words
What is it for?
Use it to inspect the latest parent session, identify its task status and next steps, and find related specifications, notes, and code files.
Why use it?
It restores important decisions, progress, and pending work when a new session lacks the previous conversation's context.

Skill for Claude CodeCodex

Part of the aichat plugin — 2 skills, 1 command, 1 agent shipped together

About the project

pchalasani/claude-code-tools is a collection of command-line tools, skills, agents, hooks, plugins, and commands for improving work with Claude Code, Codex-CLI, and similar coding agents. It is used by developers who want reusable productivity features and workflows for terminal-based AI coding assistants. The catalogue entries are components of, or extensions for, these coding-agent workflows.

pchalasani/claude-code-tools · 1,990 stars · on GitHub

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/pchalasani/claude-code-tools/recover-context
Any agent
npx skills add pchalasani/claude-code-tools --skill recover-context
Clone the repo
git clone --depth 1 https://github.com/pchalasani/claude-code-tools

Made for: Claude Code, Codex.

Or install aichat, the plugin that ships this one along with the rest of its 2 skills, 1 command, 1 agent.

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 recover-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/pchalasani/claude-code-tools/recover-context.svg)](https://agentmods.dev/skills/pchalasani/claude-code-tools/recover-context)
Your own site
<a href="https://agentmods.dev/skills/pchalasani/claude-code-tools/recover-context"><img src="https://agentmods.dev/badge/skills/pchalasani/claude-code-tools/recover-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 489 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 $0.00036 $0.00489
Opus 5 $0.00018 $0.00244
Sonnet 5 $0.00007 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured 5d ago against content hash 5761a66485b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recover-context 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 5d 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.

plugins/aichat/skills/recover-context/SKILL.md · 59 lines

What it actually says

recover-context

Use this skill to extract context from a parent session when a session lineage is present (shown in the first user message of this conversation).

Instructions

  1. Identify the most recent parent session from the lineage chain (the last file in the chronological list).

  2. Use sub-agents to explore (to avoid bloating your own context):

    • If you have the Task tool with subagent support, use the session-searcher subagent (subagent_type: session-searcher) to analyze the most recent session
    • If sub-agents are NOT available, use the aichat:session-search skill instead
  3. Extract the following from the most recent session:

    • What was the last task being worked on?
    • What was the current state of that task (completed, in-progress, blocked)?
    • Any pending items or next steps mentioned?
    • Key decisions made or approaches chosen
  4. Also check for associated documents:

    • Issue specs or task descriptions referenced in the session
    • Any markdown files created during that session (check WORKLOG/, issues/, etc.)
    • Code files that were being modified
  5. Report back concisely:

    • State your understanding of the task context
    • List any files you found that are relevant
    • Ask the user how they'd like to proceed

Example Sub-agent Prompt

If using the Task tool with session-searcher subagent:

Analyze the session file at [path from lineage] and extract:
1. The last task being worked on (look at the final 20-30 messages)
2. Current state of that task
3. Any referenced markdown files (issue specs, work logs, etc.)
4. Pending next steps or blockers

Return a concise summary.

Constraints

  • Do NOT read large session files directly into your own context
  • ALWAYS delegate to sub-agents or the session-search skill
  • Keep your summary concise - the user knows what they were working on
  • Focus on the LAST task, not the entire session history
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. 5d ago First seen · 59 lines · 36 tokens per session scan A 5761a66485b2

Subscribe to this mod's changes

recover-context is a skill published in the GitHub repository pchalasani/claude-code-tools (1,990 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 489 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

mem0-vercel-ai-sdk

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…

mem0ai/mem0 · 146 tokens

mem0-tour

Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.

mem0ai/mem0 · 47 tokens

stats

Displays memory usage statistics for the current session and project including counts by category, age distribution, and API latency. Use when checking how many memories exist, reviewing session activity, or auditing memory distribution across categories.

mem0ai/mem0 · 43 tokens

peek

Searches memories and displays compact one-liner results, or looks up a specific memory by ID. Use for quick memory lookups, checking if a decision was recorded, resolving [mem0:id] citations, or browsing memories without full category detail.

mem0ai/mem0 · 52 tokens

pause

Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.

mem0ai/mem0 · 30 tokens

mine

Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.

MemPalace/mempalace · 21 tokens