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 skills/gh33k/session-plugin/endnpx skills add gh33k/session-plugin --skill endgit clone --depth 1 https://github.com/gh33k/session-pluginWhat 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 | $0.00044 | $0.00732 |
| Opus 5 | $0.00022 | $0.00366 |
| Sonnet 5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
session:end 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 yesterday.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
session:end
Close session, capture work, update state for next session.
Quick End (/session:end quick)
Fast close, minimal interaction:
git status --short 2>/dev/null
bd list --status=in_progress --json 2>/dev/null | jq -r '.[] | .id' | head -5
Write minimal continuation to .context/continuation.md:
# Continue
Last: Quick end - no summary
In progress: {task IDs from above}
Ready: {bd ready --json --limit=3 | jq -r '.[].id'}
Suggested: /session:start build
Output:
Session closed (quick).
Uncommitted: {file count from git status}
In progress: {task IDs}
Done.
Full End (/session:end)
1. Check Work Done
git status --short 2>/dev/null
If uncommitted changes, ask: "Commit before ending?"
2. Task Review (if beads active)
bd list --status=in_progress --json 2>/dev/null
For each task, ask: "Complete? (yes/no/partial)"
- yes →
bd close <id> --reason "completed" - partial → Note what remains, leave open
- no → Leave for next session
3. Discovered Work
Ask: "New tasks or issues discovered?"
If yes → See references/discovered-work.md
4. Update State
Update .project/state.md:
- Active Focus: Next priority
- Recent Decisions: Add any made this session (date, decision, rationale)
- Blockers: Add/remove as needed
5. Update Session File
Find current: ls -t .context/sessions/*.md | head -1
Append:
## Summary
Completed: {what was done}
Closed: {task IDs}
Created: {new task IDs}
Carry forward: {next priorities}
Decisions: {key decisions made}
6. Write Continuation
Write .context/continuation.md:
# Continue
Last: {1-2 sentence summary of session work}
Focus: {from updated state.md Active Focus}
Blockers: {count} {brief list if any}
In progress: {task IDs, comma-separated}
Ready: {top 3 task IDs from bd ready}
Suggested: /session:start {type}
Context: {key files or areas touched}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 129 lines · 44 tokens per session scan A e7258c98d2bb
session:end is a skill published in the GitHub repository gh33k/session-plugin (2 stars, last pushed 7mo ago), licensed MIT. It adds 44 tokens to every session and 732 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
agent-native-architecture
Design agent-native architectures where agents are first-class citizens. Use when building autonomous agents, MCP tools, or self-modifying systems.
lavra-ceo-review
CEO/founder-mode plan review -- challenge premises, validate business fit, run 10-section structured review.
lavra-review
Perform exhaustive code reviews using multi-agent analysis and ultra-thinking.
dspy-ruby
Build type-safe LLM applications with DSPy.rb. Use when implementing AI features, LLM signatures, agent systems, or prompt optimization in Ruby.
lavra-brainstorm
Explore requirements and approaches through collaborative dialogue before planning.
lavra-knowledge
Capture solved problems as knowledge entries for fast recall. Use when a solution should be preserved for future sessions.