ai-workflow-framework: Skill for Claude Code

.claude/skills/project-insights/SKILL.md

project-insights is a skill for Claude Code from satsilem/ai-workflow-framework. It costs 126 tokens per session (1,809 once invoked), scanned A, original, MIT.

A project-maintenance review that checks operational notes, project instructions, documentation, and possible improvements to shared coding-agent guidance. It compares what is recorded with what has actually been implemented.

In plain words
What is it for?
Use it to triage INSIGHTS.md, check CLAUDE.md gaps, review documentation follow-ups, and find notes that should become permanent reference material.
Why use it?
It helps keep project notes useful by identifying completed, stale, missing, or still-open items before anything is archived or changed.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is satsilem/ai-workflow-framework's own configuration. It tells Claude Code how to work on ai-workflow-framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-workflow-framework configures →

Reuse

Borrowing it

Nothing to install: this file belongs to satsilem/ai-workflow-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/satsilem/ai-workflow-framework/main/.claude/skills/project-insights/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/satsilem/ai-workflow-framework

Made for: Claude Code.

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-insights

README.md
[![agentmods](https://agentmods.dev/badge/skills/satsilem/ai-workflow-framework/project-insights/github.svg)](https://agentmods.dev/skills/satsilem/ai-workflow-framework/project-insights)
Your own site
<a href="https://agentmods.dev/skills/satsilem/ai-workflow-framework/project-insights"><img src="https://agentmods.dev/badge/skills/satsilem/ai-workflow-framework/project-insights/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 project-insights

Your own site · 80×15
<a href="https://agentmods.dev/skills/satsilem/ai-workflow-framework/project-insights"><img src="https://agentmods.dev/badge/skills/satsilem/ai-workflow-framework/project-insights.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,809 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.
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 $0.00126 $0.01809
Opus 5.5 $0.00050 $0.00724
Sonnet 5.5 $0.00025 $0.00362
Haiku 4.5 $0.00013 $0.00181

Measured 2mo ago against content hash 5137a2d95a43, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-insights 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 2mo 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/project-insights/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Insights — Triage & Archive

Goal

Help the user keep INSIGHTS.md lean and actionable. Check what's been implemented, what's genuinely still open, and what's gone stale — then confirm with the user section by section before making any changes.


Step 1 — Gather context

Read these files in order:

  1. INSIGHTS.md in the current project directory — the items to triage
  2. Project CLAUDE.md — to check whether CLAUDE.md gap items have been filled
  3. Global agent CLAUDE.md — to check whether items were promoted there already
  4. Skills directory listing — to check whether skill candidates/upgrades exist:

ls /


If no global skills directory is configured, skip that check and continue with
project-local evidence.

For **Skill Upgrade** items, go one step further: read the relevant skill's `SKILL.md` briefly to check whether the described improvement is actually present (not just that the skill exists).

For **Automation Ideas** that mention a specific script or alias, check the shell aliases file or the relevant scripts directory.

Also check lightweight docs hygiene signals:
- `.reference/INDEX.md` exists and includes newly promoted files.
- `.reference` docs touched in recent work have updated `Last reviewed`.
- `.reference` metadata includes `Purpose`, `When to use`, `Source of truth`, `Owner`, `Confidence`, `Last reviewed`.
- Reusable docs in `.ai-notes` are flagged as promotion candidates.

---

## Step 2 — Triage each item

Go through every non-archived item in INSIGHTS.md and assign one status:

| Status | Meaning |
|--------|---------|
| ✅ Done | The improvement exists — skill built, CLAUDE.md updated, script implemented, issue resolved |
| ⏳ Open | Not yet implemented, still clearly relevant |
| 📤 Promote to global CLAUDE.md | A project-level CLAUDE.md gap that's universal enough to belong in the global CLAUDE.md |
| 🗑️ Stale | No longer relevant — project direction changed, different approach taken, or won't fix |

Read the full file on GitHub · 190 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. 2mo ago First seen · 190 lines · 126 tokens per session scan A 5137a2d95a43

Subscribe to this mod's changes

project-insights is a skill published in the GitHub repository satsilem/ai-workflow-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 1,809 once invoked, about $0.0005 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 2026-08-31.

Related

project-insights compared with skills from other repositories

project-insights next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
project-insightssatsilem/ai-workflow-frameworkSkill21mo agoMITA126Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code