project-pulse

project-pulse is a skill for Claude Code, Codex from aaronsb/claude-code-config. It costs 39 tokens per session (917 once invoked), scanned A, original, MIT.

A discovery tool that compares changes in Claude Code, an AI coding assistant, with this project's commits and architecture decision records.

In plain words
What is it for?
Use it to review new upstream releases, compare development history, identify gaps, or check whether architecture decision records are current.
Why use it?
It reveals relevant upstream changes and whether the project's documented technical decisions still match the code.

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/aaronsb/claude-code-config/project-pulse
Any agent
npx skills add aaronsb/claude-code-config --skill project-pulse
Clone the repo
git clone --depth 1 https://github.com/aaronsb/claude-code-config

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 project-pulse

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaronsb/claude-code-config/project-pulse.svg)](https://agentmods.dev/skills/aaronsb/claude-code-config/project-pulse)
Your own site
<a href="https://agentmods.dev/skills/aaronsb/claude-code-config/project-pulse"><img src="https://agentmods.dev/badge/skills/aaronsb/claude-code-config/project-pulse.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 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 $0.00039 $0.00917
Opus 5 $0.00019 $0.00458
Sonnet 5 $0.00008 $0.00183
Haiku 4.5 $0.00004 $0.00092

Measured 4d ago against content hash 55a4f364aabc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-pulse 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 4d 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/project-pulse/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Pulse

Compare this project against Claude Code upstream releases, or reconcile ADR statuses against shipped code.

Usage

/project-pulse                    # What's new upstream?
/project-pulse --inward           # Are our ADRs current?
/project-pulse --since 2026-03-01 # Wider window
/project-pulse --full             # Full history

How to Run

Execute the script and capture its output:

bash ~/.claude/scripts/project-pulse [flags]

The script outputs structured markdown. Your job is to interpret it.

Upstream Mode (default)

The script outputs:

  1. Claude Code releases in the window (with full changelogs)
  2. Our commits in the same window
  3. An epoch mapping table (our commits mapped to which upstream release was current)
  4. High-delta alerts (periods where many upstream releases passed between our commits)

Your interpretation

Read the upstream changelogs and filter through what this project cares about:

Relevant to us (suggest these):

  • Hooks: new hook types, hook behavior changes, hook lifecycle
  • Settings/config: new settings fields, managed settings, permissions model
  • Skills/slash commands: new frontmatter fields, skill discovery changes, effort levels
  • Context window: size changes, compaction behavior, token tracking
  • Plugins: marketplace changes, plugin sources, installation flow
  • Subagents/teams: isolation modes, worktree behavior, agent coordination
  • MCP: new capabilities, server management, tool patterns

Usually irrelevant (skip these):

  • UI polish, terminal rendering, keybindings
  • Voice mode, dictation
  • IDE-specific integrations (VSCode, Cursor)
  • API proxy fixes, Bedrock/Vertex specifics
  • Remote Control, bridge sessions

Output format

Pick the 2-5 most interesting upstream changes and explain in plain prose why they matter for this project. Reference the specific version. Example:

Claude Code v2.1.80 added effort frontmatter for skills. We author skills — this would let our think strategies control reasoning effort. Worth an ADR?

Read the full file on GitHub · 105 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. 4d ago First seen · 105 lines · 39 tokens per session scan A 55a4f364aabc

Subscribe to this mod's changes

project-pulse is a skill published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 917 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

t0-orchestrator

Master orchestration for the VNX multi-terminal system. Governs receipt review, quality/risk interpretation, open-items lifecycle, PR completion decisions, and single-block dispatch creation across T1/T2/T3.

Vinix24/vnx-orchestration · 48 tokens

control-centre

Multi-project Control Centre supervisor. Supervisors N per-project T0's from a single interactive Claude Code session. Read-only orchestration — no code writes.

Vinix24/vnx-orchestration · 35 tokens

horizon

Strategic owner of Horizon, the VNX future-state layer (roadmap -> tracks -> deliverables) and the plan-first gate. USE THIS when the user wants to plan the next VNX feature, decide what to build next, add something to the roadmap, prioritize or schedule (inplannen) work into now/next/later horizons, break a feature…

Vinix24/vnx-orchestration · 207 tokens

fulcra-agent-directives

Directed work for a fulcra-agent-teams space: tell an agent (or broadcast to all), schedule reminders, capture backlog, hand off with a checkpoint, and track a per-agent inbox with acks and re-notify — all deterministic.

ashfulcra/fulcra-tools · 55 tokens

fulcra-agent-reconcile

Give a fulcra-agent-teams space self-healing, queryable task views: fold changed OKF task docs from the data-updates feed, retain a fail-closed full-scan fallback, regenerate task/index.md and log.md, and answer status/board/needs-me/search in one read.

ashfulcra/fulcra-tools · 67 tokens

fulcra-agent-tasks

Give a fulcra-agent-teams space a typed task lifecycle: create tasks with structured status/priority/assignee, and move them through a validated state machine (proposed→active→done) instead of freeform markdown.

ashfulcra/fulcra-tools · 52 tokens