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 skills add animalzinc/claude-plugins --skill session-savergit clone --depth 1 https://github.com/animalzinc/claude-pluginsWrote 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.
[](https://agentmods.dev/skills/animalzinc/claude-plugins/session-saver)<a href="https://agentmods.dev/skills/animalzinc/claude-plugins/session-saver"><img src="https://agentmods.dev/badge/skills/animalzinc/claude-plugins/session-saver.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01571 |
| Opus 5 | $0.00000 | $0.00785 |
| Sonnet 5 | $0.00000 | $0.00314 |
| Haiku 4.5 | $0.00000 | $0.00157 |
Grade A, and why
session-saver 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 7d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: Session Saver description: Save a structured session log so the next session can pick up where you left off triggers:
- save session
- session summary
- pick up where I left off
- save progress
- end of session
- session log
Session Saver
You are going to produce a concise session log and SAVE IT TO A FILE in the project repository.
Remember: This session log and the codebase are the ONLY things that persist between sessions. The current conversation will be LOST. Capture any planned but unimplemented work in detail.
Task
- Session summary: Summarize today's objectives, notable prompts, key decisions, and achievements.
- Files changed: List all modified/created files with 1-line descriptions of changes.
- Referenced materials: List paths, directories, files, or links that were shared or referenced during the session but not modified. Includes workflow paths, reference documents, external URLs, and resources that provide important context.
- Technical notes: Brief notes on important discoveries, patterns used, issues resolved, or unresolved issues.
- Future plans: DETAILED capture of any unimplemented work, including:
- Exact steps planned for each future phase
- Specific implementation details discussed
- Any design decisions or approaches agreed upon
- Open items: List open questions/next actions as checkboxes.
- Metrics (if available): Number of files changed, tests added/modified, lines added/removed.
Format requirements
- Use ISO date format (YYYY-MM-DD) in the heading
- Include project path/name at the top
- Add session duration if available
- Tag the session type: [feature] [bugfix] [refactor] [docs] [config] [testing]
Output structure
## Session Log: [YYYY-MM-DD]
**Project**: [project-name or path]
**Duration**: [if available]
**Type**: [feature/bugfix/refactor/docs/config/testing]
### Objectives
- [Primary goal]
- [Secondary goals if any]
### Summary
[2-3 sentences describing what was accomplished]
### Files Changed
- `path/to/file1.ext` - Brief description of change
- `path/to/file2.ext` - Brief description of change
### Referenced Materials
*(Paths, directories, links, or resources shared/referenced this session — not modified, but important for context)*
- `path/to/workflow/directory/` - Description of what this is
- `path/to/reference/file.md` - Why it was referenced
- https://example.com/resource - External resource consulted
### Technical Notes
- [Key learning or pattern discovered]
- [Important decision made and why]
### Future Plans & Unimplemented Phases
*(Include this section only if there ARE unimplemented phases)*
#### Phase [X]: [Name]
**Status**: Not started / Partially complete
**Planned Steps**:
1. [Specific step with implementation details]
2. [Specific step with implementation details]
### Next Actions
- [ ] Todo item 1
- [ ] Todo item 2
- [ ] Question or investigation needed
### Metrics
- Files modified: X
- Files created: Y
- Tests added: Z
### Continuation Prompt
Project: [project-name]
Session log: docs/SESSION_LOG.md
Section: "## Session Log: [YYYY-MM-DD]" ([project/type] entry)
Context: [1-2 sentence summary of what we were working on]
Key points:
- [Key point 1]
- [Key point 2]
- [Key point 3 if applicable]
Referenced paths:
- [Only paths relevant to continuing this work]
Read the session log section above, familiarize yourself with the context, and let me know when ready to continue.
*(Leave sections empty if nothing to report. Delete empty sections before saving.)*
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.
- 7d ago First seen · 175 lines · 0 tokens per session scan A 3d361c10bd5d
session-saver is a skill published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,571 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 skills, from other repositories
obsidian-memory-architecture
Use when designing, setting up, or maintaining an Obsidian vault as Hermes Agent's durable knowledge layer. Routes facts, conversation history, documents, procedures, and daily logs to the correct Hermes or vault system without duplicating everything into the prompt.
meta-context-diet
Audit CLAUDE.md and .claude/rules for always-loaded content that should become an on-demand skill. Use when CLAUDE.md feels bloated, trimming context, or promoting a rule into a skill.
meta-local-notes
Audit a CLAUDE.local.md — verify each claim live, fix drifted environment facts, cut findings duplicating versioned docs. Use when local notes are stale, or before appending a finding.
memory-manager
Manage HOT/WARM/COLD memory transitions, Wiki Phase 1/2/3 entity sedimentation, GDPR Art 17 purge. Triggered by hooks/stopfinalize.py + /forget-project command.
ai-brain
Give Claude a permanent, searchable long-term memory using an Obsidian vault as the store. At the end of a session, summarize what mattered and save it as a Markdown note in your "AI Brain" vault; at the start of a session (or on demand), read back only the relevant past notes. Local markdown you own — connected via…
citedy-content-writer
From topic to published blog post in one conversation — generate SEO- and GEO-optimized articles with AI illustrations and voice-over in 55 languages, create social media adaptations for 9 platforms, set up automated content sessions, and manage product knowledge base. End-to-end blog autopilot. Powered by Citedy.