Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/captain-diaryWrote 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/leopu00/job-hunter-team/captain-diary)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/captain-diary"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/captain-diary/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/captain-diary"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/captain-diary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00117 | $0.00579 |
| Opus 5 | $0.00059 | $0.00290 |
| Sonnet 5 | $0.00023 | $0.00116 |
| Haiku 4.5 | $0.00012 | $0.00058 |
Grade A, and why
captain-diary 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 11d 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.
What it actually says
captain-diary — the handoff between Captains
One file per day in $JHT_HOME/logs/captain-diary-YYYY-MM-DD.md, append-only.
Its job is to keep you from starting over at every restart: today's pacing
lessons are handed to tomorrow's Captain.
At wake (ALWAYS, before working)
Read the notes left by the previous day's Captain:
python3 /app/shared/skills/captain_diary.py handoff
It prints yesterday's notes (or those of the last day worked) plus whatever is already recorded today. You inherit the lessons → do not repeat the same mistakes. If there is nothing, you are the first: start recording.
During the day — record the SIGNIFICANT events
One line, whenever something happens that carries a lesson. NOT a diary of everything: only what tomorrow's Captain would need.
python3 /app/shared/skills/captain_diary.py add "20:05 — 3 Scouts at once: unbrakable \
spike within 15 min, 5h of coasting to repay the debt. Lesson: max 1 Scout then \
30 min of observation (C-02)."
What is worth recording:
- scaling decisions that went badly (or well) — how many workers, which throttle, what happened;
- a spike you could not brake and how you recovered from it;
- a kill and why;
- a pattern that emerged (e.g. "the Scout on site X consumes twice as much");
- anything that, if you knew it tomorrow, would avoid a mistake.
Reviewing today only
python3 /app/shared/skills/captain_diary.py today
Rule
- The diary is the baton: read it at boot, feed it during the day.
- Notes must be short and actionable (one fact + the lesson), not a verbose log.
- The timestamp is added by the tool: you write only the fact and the lesson.
What ships with it
6 files 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.
- 11d ago First seen · 54 lines · 117 tokens per session scan A 09a0d174593d
captain-diary is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 3d ago), licensed MIT. It adds 117 tokens to every session and 579 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
obsidian
Use the official Obsidian CLI (v1.12+) to manage vaults, notes, daily notes, search, tasks, tags, properties, links, templates, sync, publish, and workspaces. Use when the user mentions Obsidian, vaults, notes, or wants to automate note-taking and knowledge base workflows.
contextdb-autopilot
Automatic ContextDB session lifecycle — init, session events, checkpoints, and continuity artifacts. Use when you need AIOS context persistence without prompt injection. NOT for general task execution — only for ContextDB session management. TRIGGER: contextdb、session persist、checkpoint save.
memo
AIOS project memory — read/write/search your own memory using the memo capabilities. You (the model) decide what to remember, what to correct, and what was useful; the harness only executes your decision. Use when you want to recall prior work, persist a durable fact, supersede a wrong one, or mark a recalled memory…
aios-offload-recall
Use when recalling prior AIOS tool/browser outputs from offloaded refs; inspect Mermaid canvas first, then read only matching node-level evidence.
context-search
A continuity workflow for finding context from earlier coding-agent sessions. It can inspect continuation notes and session records when a task refers to previous work.