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.
npx agentmods add commands/agentsea/flashbacker/working-plangit clone --depth 1 https://github.com/agentsea/flashbackerWhat 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.
| Model | Per session | Once 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 |
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 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
- Read the AI analysis prompt: Load
.claude/flashback/prompts/working-plan-update.mdfor detailed analysis instructions - Read current working plan: Load
.claude/flashback/memory/WORKING_PLAN.mdto understand current state - Gather session context: Use
flashback working-plan --contextto get recent conversation transcript - Analyze conversation: Extract what was actually accomplished, decisions made, next steps identified
- 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 templateflashback 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.
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.
- 2d ago First seen · 40 lines · 0 tokens per session scan B 19cd878d7a9f
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.
Other commands, from other repositories
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
new
Creates a new item in a module that supports the new capability.
card
Open one self-contained OverClick card.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.