boss-briefing

boss-briefing is a skill for Claude Code from sehoon787/my-claude. It costs 23 tokens per session (1,580 once invoked), scanned A, original, MIT.

A project knowledge-base health check for the `.briefing/` vault, the folder used to store persistent project notes.

In plain words
What is it for?
Use it to read session state, detect gaps since the previous session, analyze workflow patterns, and propose rules for how the coding agent should work.
Why use it?
It finds missing session context, analyzes work patterns, and keeps the project profile and notes in sync.

Skill for Claude Code

Written for Claude Code: effort in frontmatter.

Part of the my-claude plugin — 4 skills, 8 hooks, 3 MCP servers shipped together

Good fit Use it to read session state, detect gaps since the previous session, analyze workflow patterns, and propose rules for how the coding agent should work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sehoon787/my-claude/boss-briefing
Install

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.

Any agent
npx skills add sehoon787/my-claude --skill boss-briefing
Clone the repo
git clone --depth 1 https://github.com/sehoon787/my-claude

Made for: Claude Code.

Or install my-claude, the plugin that ships this one along with the rest of its 4 skills, 8 hooks, 3 MCP servers.

Wrote 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.

agentmods badge for boss-briefing

README.md
[![agentmods](https://agentmods.dev/badge/skills/sehoon787/my-claude/boss-briefing/github.svg)](https://agentmods.dev/skills/sehoon787/my-claude/boss-briefing)
Your own site
<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.

agentmods 80×15 button for boss-briefing

Your own site · 80×15
<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>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,580 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.01580
Opus 5 $0.00012 $0.00790
Sonnet 5 $0.00005 $0.00316
Haiku 4.5 $0.00002 $0.00158

Measured 11d ago against content hash 2782266cb7e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 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.

skills/core/boss-briefing/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 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-vault handles vault templates and initialization
  • boss-briefing handles sync, analysis, and pattern detection
  • stop-profile-update.js still 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 date
  • workCounter — file edit count this session
  • sessionMessageCount — user message count this session
  • lastVaultSync — ISO timestamp of last /boss-briefing run
  • sessionStartHead — git HEAD or YYYY-MM-DD:cwd identifier

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:

  1. Scan .briefing/sessions/ for the most recent session file (by filename date prefix)
  2. Report the gap: "Last session was on YYYY-MM-DD (N days ago). Topic: "
  3. 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.

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.

Sequence patterns: Look for recurring ordered sub-sequences (length >= 2) that appear in >= 2 different sessions/days. Examples:

  • "explore → executor" (seen 4 times)
  • "explore → executor → code-reviewer" (seen 3 times)
  • "planner → executor → code-reviewer" (seen 2 times)

Read the full file on GitHub · 160 lines

Changes

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.

  1. 11d ago First seen · 160 lines · 23 tokens per session scan A 2782266cb7e5

Subscribe to this mod's changes

boss-briefing is a skill published in the GitHub repository sehoon787/my-claude (16 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,580 once invoked, about $0.0001 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.