working-plan

A project-management helper that updates a development working plan from the current conversation and project state. It reads the plan, reviews recent work, and records completed tasks, ongoing work, decisions, and next steps.

In plain words
What is it for?
Use it to review session progress, update a working-plan file, archive older plans, or remove older archived plans.
Why use it?
Working plans become inaccurate when they are updated from memory or only reflect timestamps. This keeps the plan aligned with what actually happened.

Command for Claude Code

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 commands/agentsea/flashbacker/working-plan
Clone the repo
git clone --depth 1 https://github.com/agentsea/flashbacker

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.00458
Opus 5 $0.00000 $0.00229
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 2d ago against content hash 19cd878d7a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

working-plan scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

## Output Instructions
templates/.claude/commands/fb/working-plan.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working Plan Update

You are an expert project manager updating a development working plan based on conversation analysis.

Task

  1. Read the AI analysis prompt: Load .claude/flashback/prompts/working-plan-update.md for detailed analysis instructions
  2. Read current working plan: Load .claude/flashback/memory/WORKING_PLAN.md to understand current state
  3. Gather session context: Use flashback working-plan --context to get recent conversation transcript
  4. Analyze conversation: Extract what was actually accomplished, decisions made, next steps identified
  5. Update working plan: Apply changes to reflect real session progress, not just timestamp updates

Archive Management Commands

For manual plan management:

  • flashback working-plan --archive - Archive current plan to .claude/flashback/memory/ARCHIVE/plans/ and create fresh template
  • flashback working-plan --prune 5 - Keep only 5 most recent archived plans (default: 10)

Analysis Focus

From recent conversation, identify:

  • Completed Tasks: What was actually finished or implemented
  • In-Progress Work: Tasks started but not completed
  • Key Decisions: Important architectural or design decisions made
  • Blockers: Issues or obstacles encountered
  • Next Steps: Explicitly mentioned or implied next actions
  • Scope Changes: Any changes to project direction or priorities

Output Instructions

YOU MUST WRITE THE COMPLETE UPDATED .claude/flashback/memory/WORKING_PLAN.md FILE.

After analyzing the conversation, output the entire updated working plan file with these changes:

  • Move completed tasks from "Next Priorities" to "Completed Recently"
  • Update "Current Phase" if phase changed
  • Refresh "Immediate Tasks" based on conversation
  • Add new tasks discovered during session
  • Update session reference and timestamp
  • Preserve overall structure and formatting

CRITICAL: Always output the complete, updated WORKING_PLAN.md file content. Do not just provide analysis - write the actual file that should replace the existing one.

Read the full file on GitHub · 40 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. 2d ago First seen · 40 lines · 0 tokens per session scan B 19cd878d7a9f

Subscribe to this mod's changes

working-plan is a command published in the GitHub repository agentsea/flashbacker (57 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 458 tokens. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.