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.
npx agentmods add skills/zeusyue/acceptance-driven-development-skill/project-experiencenpx skills add ZeusYue/acceptance-driven-development-skill --skill project-experiencegit clone --depth 1 https://github.com/ZeusYue/acceptance-driven-development-skillWrote 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.
[](https://agentmods.dev/skills/zeusyue/acceptance-driven-development-skill/project-experience)<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>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.
| Model | Per session | Once 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 |
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.
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.
- Read
~/.add-hub. A trimmed path naming an existing directory is authoritative. - If the pointer is missing or stale, search for
**/_exp_memory.mdunder the user's home directory. Validate candidate parents by checking for hub templates and<ProjectName>/AC.mdor<ProjectName>/<ProjectName>.mdfiles. - If one candidate validates, use it and write
~/.add-hub. If none or multiple remain, ask the user to choose a stable shared directory. - 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.
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.
- today Changed · -190 lines · -1 tokens per session bb3877eb10dd
- 5d ago First seen · 306 lines · 72 tokens per session scan A fe8428e2e73e
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.
Other skills, from other repositories
subagents-orchestration-guide
Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.
ai-development-guide
Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.
integration-e2e-testing
Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.
recipe-diagnose
Investigate problem, verify findings, and derive solutions.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.