project-experience

project-experience is a skill for Claude Code, Codex from ZeusYue/acceptance-driven-development-skill. It costs 71 tokens per session (1,417 once invoked), scanned A, original, MIT.

A tool that reads a project’s existing documentation and prepares a briefing before code or architecture work begins. The documents can describe the project’s technology, structure, reusable patterns, conventions, and known problems.

In plain words
What is it for?
Use it before writing code, designing architecture, choosing dependencies, or implementing features when the project has a documentation library. It also refreshes the project’s experience memory file.
Why use it?
It reduces the chance of making decisions that conflict with lessons already recorded for the project. It helps an agent use local project knowledge instead of relying only on general assumptions.

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/zeusyue/acceptance-driven-development-skill/project-experience
Any agent
npx skills add ZeusYue/acceptance-driven-development-skill --skill project-experience
Clone the repo
git clone --depth 1 https://github.com/ZeusYue/acceptance-driven-development-skill

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-experience

README.md
[![agentmods](https://agentmods.dev/badge/skills/zeusyue/acceptance-driven-development-skill/project-experience.svg)](https://agentmods.dev/skills/zeusyue/acceptance-driven-development-skill/project-experience)
Your own site
<a href="https://agentmods.dev/skills/zeusyue/acceptance-driven-development-skill/project-experience"><img src="https://agentmods.dev/badge/skills/zeusyue/acceptance-driven-development-skill/project-experience.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,417 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 5.1 $0.00071 $0.01417
Opus 5 $0.00036 $0.00709
Sonnet 5 $0.00014 $0.00283
Haiku 4.5 $0.00007 $0.00142

Measured today against content hash bb3877eb10dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

project-experience 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 today.

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-experience/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Experience

Research evidence-backed lessons across the shared project-document library and maintain its compact global cache.

Boundary: ADD reads _exp_memory.md once per new Agent/session and owns each _<ProjectName>_exp.md project capsule. This skill performs explicit cross-project research or an approved global-cache refresh; it does not author project documents, project capsules, AC state, or implementation plans.

Use and skip

Use this skill when the user explicitly asks to:

  • compare prior projects or find reusable cross-project lessons;
  • investigate whether a past project solved a similar problem;
  • refresh, rebuild, or audit _exp_memory.md;
  • complete an ADD-approved global-cache refresh.

Skip it for ordinary implementation, architecture work inside one known project, Mode A/Mode B execution, small fixes, documentation edits, or a request already covered by the project's capsule. ADD remains functional when this skill is absent.

Phase 0: Locate the shared document hub

All project documents and the global experience cache live under one shared document hub ($DOC_HUB), which may be an Obsidian vault or plain directory. Use canonical absolute paths with shell/filesystem tools; when a host accepts only workspace-relative vault paths, use that supported form without changing Hub identity.

  1. Read ~/.add-hub. A trimmed path naming an existing directory is authoritative.
  2. If the pointer is missing or stale, search for **/_exp_memory.md under the user's home directory. Validate candidate parents by checking for hub templates and <ProjectName>/AC.md or <ProjectName>/<ProjectName>.md files.
  3. If one candidate validates, use it and write ~/.add-hub. If none or multiple remain, ask the user to choose a stable shared directory.
  4. For a new hub, create the directory, create an empty _exp_memory.md, and write the pointer.

Cache presence helps fallback discovery but never overrides a valid pointer or proves Hub identity by itself.

Read the full file on GitHub · 116 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. today Changed · -190 lines · -1 tokens per session bb3877eb10dd
  2. 5d ago First seen · 306 lines · 72 tokens per session scan A fe8428e2e73e

Subscribe to this mod's changes

project-experience is a skill published in the GitHub repository ZeusYue/acceptance-driven-development-skill (6 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,417 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.