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/itechmeat/open-second-brain/agent-event-lognpx skills add itechmeat/open-second-brain --skill agent-event-loggit clone --depth 1 https://github.com/itechmeat/open-second-brainWrote 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/itechmeat/open-second-brain/agent-event-log)<a href="https://agentmods.dev/skills/itechmeat/open-second-brain/agent-event-log"><img src="https://agentmods.dev/badge/skills/itechmeat/open-second-brain/agent-event-log.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 | $0.00266 | $0.01329 |
| Opus 5 | $0.00133 | $0.00665 |
| Sonnet 5 | $0.00053 | $0.00266 |
| Haiku 4.5 | $0.00027 | $0.00133 |
Grade B, and why
agent-event-log 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Config / deployment:** any change to `config.yaml`, `~/.codex/config.toml`, systemd unit, Caddy snippet, environment variable, secret rotation, infra rollout. How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Event Log
Open Second Brain ships an event_log_append tool (via the MCP server registered by this plugin) that records what happened, when, and which agent did it. The tool writes one line into the day's Markdown note (<vault>/Daily/YYYY.MM.DD.md) under a ## Raw events heading.
When to call event_log_append
Call it once per durable artifact produced in the current turn. A durable artifact is anything you would want to find again by searching the vault tomorrow, next week, or six months from now. Concrete triggers:
- Code: code shipped, bug fixed, refactor merged, dependency bumped, schema migration applied.
- Config / deployment: any change to
config.yaml,~/.codex/config.toml, systemd unit, Caddy snippet, environment variable, secret rotation, infra rollout. - Instructions / docs: edit to
CLAUDE.md,AGENTS.md, project README, plugin docs, system prompt, runbook, onboarding guide. - Content artifacts: new post draft, documentation page, marketing copy, release notes, public-facing communication.
- Research / investigation findings: a concrete answer, root cause, design decision, or trade-off resolution. Not the act of searching — the conclusion you reached.
- External-fact discoveries: a CLI now requires a flag it didn't before, an API rejects a payload it used to accept, a documented behavior diverges from observed behavior. Worth logging because the next session won't re-discover it.
When NOT to call it
- Pure discussion or brainstorming with no conclusion.
- Read-only queries (running
git log,o2b status,vault_health,second_brain_query). - Planning that has not yet produced a written artifact.
- Acknowledgement-only replies ("ok", "got it").
If you are unsure: ask yourself "would future-me want to find this in the log by searching for it later?". If yes, call the tool.
How to call it
The MCP server resolves the agent identity from ~/.config/open-second-brain/config.yaml automatically; you do not pass agent unless you are deliberately logging on someone else's behalf. Pass only message:
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.
- 3d ago First seen · 75 lines · 266 tokens per session scan B 1c9385e52fe3
agent-event-log is a skill published in the GitHub repository itechmeat/open-second-brain (385 stars, last pushed 6d ago), licensed MIT. It adds 266 tokens to every session and 1,329 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…