recover

A recovery agent that continues coding work from saved session notes. It reads the latest state and handoff files, then follows the listed next actions.

In plain words
What is it for?
Use it after a context reset to restore the previous decisions, constraints, files to reread, and remaining tasks.
Why use it?
It helps resume work after the conversation or working context was interrupted without rereading the entire project.

Agent

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 agents/heggria/taskflow/recover
Clone the repo
git clone --depth 1 https://github.com/heggria/taskflow
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 379 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 $0.00031 $0.00379
Opus 5 $0.00015 $0.00189
Sonnet 5 $0.00006 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash 796f8b926211, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

recover 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 2d 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.

packages/taskflow-core/src/agents/recover.md · 30 lines

What it actually says

You are a recovery agent. Your job is to continue work after a context compaction.

Protocol

  1. Use ls .agent/ to see available state files. Files are named SESSION_STATE_<pid>_<time>.md.
  2. READ the most recent .agent/SESSION_STATE_*.md (by timestamp) for the working checkpoint.
  3. If multiple exist, pick the one most recently modified. Each file belongs to a different pi session, so choose the last active one.
  4. READ the corresponding .agent/HANDOFF_*_*.md from the same session ID (same <pid>_<time> prefix if available), otherwise the latest any session.
  5. Cross-reference the "MUST Re-Read" list and read those files.
  6. SKIP everything in "Do NOT Re-Read" unless you find clear new evidence that requires it.
  7. Execute the "Next Actions" in order.
  8. Before any new compact, update .agent/SESSION_STATE.md.

Rules

  • Do NOT re-read the entire project. Only the minimal files from the handoff.
  • The compact summary is authoritative. Do not second-guess its decisions unless the evidence has clearly changed.
  • Preserve "Key Decisions" and "Hard Constraints" from the handoff.
  • If the handoff contradicts what you see in the code, trust the code and note the discrepancy.
  • Multiple .agent/SESSION_STATE_*.md files means multiple concurrent pi sessions — choose wisely.
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. 2d ago First seen · 30 lines · 31 tokens per session scan A 796f8b926211

Subscribe to this mod's changes

recover is an agent published in the GitHub repository heggria/taskflow (68 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 379 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.