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/save-sessiongit 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 | $0.00943 |
| Opus 5 | $0.00000 | $0.00472 |
| Sonnet 5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
save-session 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Session
Create a beautifully formatted session summary document in this conversation capturing meaningful insights.
Task Workflow
- Check for Existing Session: First check if there's an existing session file to archive
- Archive Previous Session: If found, save it to archive before creating new summary
- Gather Context: Run
flashback save-session --contextto get comprehensive session data - Analyze Session: Extract real accomplishments, file changes, and decisions made
- Create New Summary: Output polished session documentation directly in this conversation
- Save Session Record: Write the formatted summary to
.claude/flashback/memory/CURRENT_SESSION.md
Session File Management
Before creating the new session summary:
- Check for existing session: Use Read tool to check if
.claude/flashback/memory/CURRENT_SESSION.mdexists - Archive if found: If file exists, copy it to
.claude/flashback/memory/ARCHIVE/sessions/session-[timestamp].md - Clean old archives: Keep only the 10 most recent archived sessions (delete older ones)
After creating the session summary:
- Save the formatted document to
.claude/flashback/memory/CURRENT_SESSION.mdfor future archiving
Manual Commands (Alternative)
If the built-in archiving above fails, you can use:
flashback save-session --archive- Manually archive session filesflashback save-session --prune 5- Manually prune old archived sessions
Note: The primary workflow handles archiving automatically in the prompt above.
Context Gathering
flashback save-session --context
Provides comprehensive session data:
- Enhanced Analysis Prompt: Detailed instructions for creating beautiful documentation
- Project Context: Memory and working plan for background
- Conversation Logs: Complete session transcript with tool calls
- Git Analysis: Actual file changes and repository state
- Tool Usage Tracking: All Edit, Write, Bash, and other tool calls made
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 · 104 lines · 0 tokens per session scan A 1de47784502e
save-session 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 943 tokens. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.