deciduous: Command for Claude Code

.claude/commands/recover.md

recover is a command for Claude Code from notactuallytreyanastasio/deciduous. It costs 14 tokens per session (1,589 once invoked), scanned A, original, Apache-2.0.

A session-start command that rebuilds project context from a decision graph and recent command history.

In plain words
What is it for?
Use it to review decisions, branch-specific context, recent commands, attached documents, and possible gaps in the project record.
Why use it?
It helps you recover important choices and unfinished work after starting a new coding session or switching branches.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

This is notactuallytreyanastasio/deciduous's own configuration. It tells Claude Code how to work on deciduous itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything deciduous configures →

Reuse

Borrowing it

Nothing to install: this file belongs to notactuallytreyanastasio/deciduous. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/notactuallytreyanastasio/deciduous/main/.claude/commands/recover.md
Clone the repo
git clone --depth 1 https://github.com/notactuallytreyanastasio/deciduous

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/notactuallytreyanastasio/deciduous/recover/github.svg)](https://agentmods.dev/commands/notactuallytreyanastasio/deciduous/recover)
Your own site
<a href="https://agentmods.dev/commands/notactuallytreyanastasio/deciduous/recover"><img src="https://agentmods.dev/badge/commands/notactuallytreyanastasio/deciduous/recover/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for recover

Your own site · 80×15
<a href="https://agentmods.dev/commands/notactuallytreyanastasio/deciduous/recover"><img src="https://agentmods.dev/badge/commands/notactuallytreyanastasio/deciduous/recover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,589 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 $0.00014 $0.01589
Opus 5.5 $0.00006 $0.00636
Sonnet 5.5 $0.00003 $0.00318
Haiku 4.5 $0.00001 $0.00159

Measured 13d ago against content hash 55c742143192, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 13d 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.

.claude/commands/recover.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Recovery

RUN THIS AT SESSION START. The decision graph is your persistent memory.

Step 1: Query the Graph

# The graph lives on the server; refresh this machine's cache first
deciduous remote pull
deciduous remote status

# See all decisions (look for recent ones and pending status)
deciduous nodes

# Filter by current branch (useful for feature work)
deciduous nodes --branch $(git rev-parse --abbrev-ref HEAD)

# See how decisions connect
deciduous edges

# What commands were recently run?
deciduous commands

# Check for attached documents
deciduous doc list

Branch-scoped context: If working on a feature branch, filter nodes to see only decisions relevant to this branch. Main branch nodes are tagged with [branch: main].

Step 1.5: Audit Graph Integrity

CRITICAL: Check that all nodes are logically connected.

# Find nodes with no incoming edges (potential missing connections)
deciduous edges | cut -d'>' -f2 | cut -d' ' -f2 | sort -u > /tmp/has_parent.txt
deciduous nodes | tail -n+3 | awk '{print $1}' | while read id; do
  grep -q "^$id$" /tmp/has_parent.txt || echo "CHECK: $id"
done

Review each flagged node (flow: goal -> options -> decision -> actions -> outcomes):

  • Root goal nodes are VALID without parents
  • option nodes MUST link to their parent goal
  • decision nodes MUST link from the option(s) being chosen
  • action nodes MUST link to their parent decision
  • outcome nodes MUST link back to their action

Fix missing connections:

deciduous link <parent_id> <child_id> -r "Retroactive connection - <reason>"

Step 1.6: Import Sessions the Graph Does Not Have

A session that logged little still left a transcript. Import what is missing before reading the graph, so the graph is complete when you read it.

deciduous transcript list                 # "new" = not yet imported
deciduous transcript import <session-id>  # goals, actions, outcomes, each with its evidence

Derived nodes say in metadata.evidence.kind whether they are proven (a tool call and its result) or inferred (the assistant's own words). Trust the proven ones.

Read the full file on GitHub · 203 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. 13d ago Changed · +8 lines 55c742143192
  2. 1mo ago Changed · +12 lines c65984d79832
  3. 1mo ago Changed c3b2044e5b38
  4. 2mo ago Changed · -7 lines e1d92ba1ef0c
  5. 2mo ago First seen · 190 lines · 14 tokens per session scan A 55d805c33f70

Subscribe to this mod's changes

recover is a command published in the GitHub repository notactuallytreyanastasio/deciduous (169 stars, last pushed 13d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,589 once invoked, about $0.0001 per session on Opus 5.5. 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

recover compared with commands from other repositories

recover next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
recovernotactuallytreyanastasio/deciduousCommand16913d agoApache-2.0A14Claude Code
minutes-ideassilverstein/minutesCommand1.6kyesterdayMITA48Claude Code, OpenCode
learnReflexioAI/claude-smartCommand7913d agoApache-2.0A14Claude Code
memory-storeverygoodplugins/mcp-automemCommand66todayMITA10Claude Code
analyze-contextRohiRIK/OpenLtmCommand298d agoMITA39Claude Code
cc-memoryTheLobbi/claudeCommand217d agoMITA0Claude Code
lians-recallLians-ai/LiansCommand174d agoApache-2.0A19Claude Code