update-briefs

update-briefs is a skill for Claude Code, Codex from rbah31/claude-code-workflow. It costs 77 tokens per session (822 once invoked), scanned A, original, Apache-2.0.

A workflow that updates a shared project-memory folder after a development sprint. It reads the sprint’s plans, results, reviews, fixes, and retrospectives, then records the current project state.

In plain words
What is it for?
Use it after a sprint, after capturing lessons, or when you need to synchronize project state and update the shared briefs.
Why use it?
Other coding agents can miss what changed during a sprint when project notes are outdated. A structured state file gives them a common summary of completed work, issues, and priorities.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/rbah31/claude-code-workflow/update-briefs
Any agent
npx skills add rbah31/claude-code-workflow --skill update-briefs
Clone the repo
git clone --depth 1 https://github.com/rbah31/claude-code-workflow

Made for: Claude Code, Codex.

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 update-briefs

README.md
[![agentmods](https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/update-briefs.svg)](https://agentmods.dev/skills/rbah31/claude-code-workflow/update-briefs)
Your own site
<a href="https://agentmods.dev/skills/rbah31/claude-code-workflow/update-briefs"><img src="https://agentmods.dev/badge/skills/rbah31/claude-code-workflow/update-briefs.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 822 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00077 $0.00822
Opus 5 $0.00039 $0.00411
Sonnet 5 $0.00015 $0.00164
Haiku 4.5 $0.00008 $0.00082

Measured 5d ago against content hash 3dbf742d7e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-briefs 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 5d 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.

.claude/skills/update-briefs/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Briefs

You are updating the shared memory (briefs/) after a sprint. Your job is to keep all strategic agents informed of the current project state.

Step 1 — Determine current sprint

Find the latest sprint directory in tasks/sprints/ (highest number).

Step 2 — Read sprint outputs

Read ALL available sprint output files:

  1. tasks/sprints/sprint-XX/plan.md
  2. tasks/sprints/sprint-XX/build-output.md
  3. tasks/sprints/sprint-XX/review-output.md
  4. tasks/sprints/sprint-XX/fix-output.md
  5. tasks/sprints/sprint-XX/redteam-output.md (if exists)
  6. tasks/sprints/sprint-XX/retrospective.md (if exists)

Also read the current briefs/project-state.md.

Step 3 — Update project-state.md

Overwrite briefs/project-state.md with:

# Project State

Last updated: [date] — Sprint [XX]

## Current state
[What the project does right now, what's deployed, what works]

## Last sprint summary
Sprint [XX]: [theme]
- Completed: [tasks done]
- Issues found: [critical/major from review]
- Tests: [passing/failing count if known]

## Open items
- [Deferred issues from review/fix]
- [Items added to backlog]

## Next priorities
- [What should be done next based on backlog + retro]

## Blockers (manual actions needed)
- [Things that require human intervention]

Step 4 — Update marketing-sync.md

Append to briefs/marketing-sync.md with user-facing changes only:

### Sprint [XX] — [Date]
**User-facing changes**:
- [New feature / fix visible to users]

**Messaging angle**: [How to communicate this]

**Not for marketing** (internal only):
- [Technical changes not relevant to users]

If the sprint had no user-facing changes, skip this step.

Step 5 — Update blockers.md

If any manual actions were discovered during the sprint (deploy steps, config changes, external service setup), append to briefs/blockers.md.

Step 6 — Update decisions-log.md

Append technical decisions made during the sprint to briefs/decisions-log.md.

Read the full file on GitHub · 109 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. 5d ago First seen · 109 lines · 77 tokens per session scan A 3dbf742d7e5d

Subscribe to this mod's changes

update-briefs is a skill published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 822 once invoked, about $0.0004 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.