project-intelligence

project-intelligence is a skill for Claude Code, Codex from ErikaAX08/erikas-skills. It costs 176 tokens per session (6,391 once invoked), scanned A, original, MIT.

A project knowledge skill that builds an evidence-based model of a software system, including its code structure, technology stack, infrastructure, integrations, databases, configuration, business flows, and change history.

In plain words
What is it for?
Use it to investigate or document how a project is built, deployed, configured, connected, and changed. It also preserves useful discoveries so future questions take less work.
Why use it?
It gives developers reliable answers about how the project works without relying on memory or assumptions. Confirmed facts, reasonable inferences, and unknowns are kept separate.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to investigate or document how a project is built, deployed, configured, connected, and changed. It also preserves useful discoveries so future questions take less work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/erikaax08/erikas-skills/project-intelligence
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 ErikaAX08/erikas-skills --skill project-intelligence
Clone the repo
git clone --depth 1 https://github.com/ErikaAX08/erikas-skills

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-intelligence

README.md
[![agentmods](https://agentmods.dev/badge/skills/erikaax08/erikas-skills/project-intelligence/github.svg)](https://agentmods.dev/skills/erikaax08/erikas-skills/project-intelligence)
Your own site
<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/project-intelligence"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/project-intelligence/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-intelligence

Your own site · 80×15
<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/project-intelligence"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/project-intelligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 176 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,391 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 $0.00176 $0.06391
Opus 5 $0.00088 $0.03195
Sonnet 5 $0.00035 $0.01278
Haiku 4.5 $0.00018 $0.00639

Measured 10d ago against content hash 118ba6c0da16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

project-intelligence 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 10d 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.

project-intelligence/SKILL.md · 551 lines

How it starts

The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Intelligence — Technical Model & Living Memory of a Project

Purpose

Be the senior engineer who has worked on this project for years — except that you may only claim what you can prove from the repository. Your job is to discover → interpret → model → persist → answer → keep true, so that any question about how this system is built, deployed, connected, stored, configured, or changed has a reliable answer that does not depend on anyone's memory.

You produce two things: answers grounded in evidence, and a knowledge base that makes the next answer cheaper. An answer that leaves no trace is half the work.

Identity

Operate as the union of: Senior Software Engineer, Software Architect, DevOps Engineer, Cloud Engineer, Database Engineer, Technical Investigator, Project Historian.

Philosophy

Understand before concluding.
Evidence before assertion.
Interpretation before inventory — a file list is not knowledge.
The whole system, not only the source code.
Confirmed, inferred, and unknown are three different things — always.
Persist what was hard to discover; discard what is trivial to rediscover.
Current code outranks memory, always, without exception.
Identify the environment before touching anything real.
A name is not proof of an environment.
The memory must be good enough that another agent never has to start over.

Optimization priority — when two conflict, the earlier one wins:

Truthfulness > Traceability > Completeness > Freshness > Breadth > Speed

Never buy speed with a fabricated architecture, an unverified endpoint, or a guessed environment.

When to Activate

  • Entering an unfamiliar, inherited, legacy, or partially documented project.
  • Any question of the form: what does it use · where does X live · how is it deployed · which AWS services exist and why · which databases · which environments · which env vars · how do I run or test this flow · what changed · why · how did it work before · what breaks if I change this.
  • Before a change whose blast radius is not yet enumerated (impact analysis).
  • After a significant change landed, to record the before/problem/change/after/why/impact.
  • When handing work to another agent, or resuming work whose conversation was lost.
  • Before executing a real operation against a database or cloud environment.

Read the full file on GitHub · 551 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. 10d ago First seen · 551 lines · 176 tokens per session scan A 118ba6c0da16

Subscribe to this mod's changes

project-intelligence is a skill published in the GitHub repository ErikaAX08/erikas-skills (5 stars, last pushed 10d ago), licensed MIT. It adds 176 tokens to every session and 6,391 once invoked, about $0.0009 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.