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 sehoon787/my-claude --skill boss-briefinggit clone --depth 1 https://github.com/sehoon787/my-claudeWrote 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/sehoon787/my-claude/boss-briefing)<a href="https://agentmods.dev/skills/sehoon787/my-claude/boss-briefing"><img src="https://agentmods.dev/badge/skills/sehoon787/my-claude/boss-briefing/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/sehoon787/my-claude/boss-briefing"><img src="https://agentmods.dev/badge/skills/sehoon787/my-claude/boss-briefing.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 | $0.00023 | $0.01635 |
| Opus 5.5 | $0.00009 | $0.00654 |
| Sonnet 5.5 | $0.00005 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00163 |
Grade A, and why
boss-briefing 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 28d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
boss-briefing
Vault health check skill. Analyzes workflow patterns, syncs profile, recovers from session gaps, and proposes persona rules based on temporal agent call sequences.
Relationship with other skills:
briefing-vaulthandles vault templates and initializationboss-briefinghandles sync, analysis, and pattern detectionstop-profile-update.jsstill runs as a fallback if this skill was not invoked during the session
Steps
Execute all 9 steps in order. If any step fails due to missing data, log the issue and continue to the next step.
Step 1: Read state.json
Read .briefing/state.json to get session metadata:
date— last session dateworkCounter— file edit count this sessionsessionMessageCount— user message count this sessionlastVaultSync— ISO timestamp of last /boss-briefing runsessionStartHead— git HEAD orYYYY-MM-DD:cwdidentifier
If state.json does not exist or is empty, use defaults: { date: "", workCounter: 0, sessionMessageCount: 0, lastVaultSync: "", sessionStartHead: "" }.
Step 2: Previous session gap detection
Compare the date field from state.json with today's date.
If the gap is >= 1 day:
- Scan
.briefing/sessions/for the most recent session file (by filename date prefix) - Report the gap: "Last session was on YYYY-MM-DD (N days ago). Topic: "
- Read the most recent session file and provide a brief recovery summary of what was last worked on
If gap is 0 (same day), skip this step.
Step 3: Analyze agent-log.jsonl sequences
Read .briefing/agents/agent-log.jsonl. Parse all entries from the last 30 days.
Count each agent_id once: SubagentStop fires again every time a teammate goes idle. Skip entries whose agent_type is not an installed agent type — older lines recorded a named agent's display name there (newer lines keep it in name).
Group entries by date. For each day, extract the ordered sequence of agent_type values.
Frequency patterns: Identify any agent_type that appears >= 3 times in the last 7 days.
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.
- 28d ago Changed · +2 lines 0d140fb820a5
- 1mo ago First seen · 160 lines · 23 tokens per session scan A 2782266cb7e5
boss-briefing is a skill published in the GitHub repository sehoon787/my-claude (17 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 1,635 once invoked, about $0.0001 per session on Opus 5.5. 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
knowledge-wiki
A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.
team-memory-protocol
A shared-memory process for teams of coding agents working on the same build. It stores project knowledge, shared context, and task progress in separate files or repositories.
fresh-start
Continue in a new chat without losing anything — writes a compact handoff to paste into a fresh conversation. Use whenever the user wants to move to a new chat or conversation, hits usage limits, says replies got slow or Claude forgets earlier details, or the conversation has grown long.
doc-digest
Turn a long document, PDF, transcript, spreadsheet or log into a compact working digest the conversation can continue from. Use when the user shares or pastes something long (several pages or more) and wants to discuss, analyze, compare or use it over more than one message, or asks to summarize a document so they can…
project-context
Turn background the user keeps re-explaining or re-pasting into reusable instructions, so new chats start with it for free. Use when the user repeats the same context, rules, style guide, persona or reference text across messages or chats, says they are tired of explaining the same thing, or asks how to set up a…
token-check
Estimate how many tokens a pasted text, an attached file or the conversation so far takes, what it means for the context window and usage limits, and how to cut it. Use when the user asks how big something is in tokens, why they keep hitting limits, or whether a file is too large to send.