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 skills add Hadi99K/AGENT_SKILLS --skill project-scaffoldgit clone --depth 1 https://github.com/Hadi99K/AGENT_SKILLSWrote 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/hadi99k/agent_skills/project-scaffold)<a href="https://agentmods.dev/skills/hadi99k/agent_skills/project-scaffold"><img src="https://agentmods.dev/badge/skills/hadi99k/agent_skills/project-scaffold/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.
<a href="https://agentmods.dev/skills/hadi99k/agent_skills/project-scaffold"><img src="https://agentmods.dev/badge/skills/hadi99k/agent_skills/project-scaffold.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00075 | $0.02637 |
| Opus 5.5 | $0.00030 | $0.01055 |
| Sonnet 5.5 | $0.00015 | $0.00527 |
| Haiku 4.5 | $0.00007 | $0.00264 |
Grade A, and why
project-scaffold 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.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🏗️ Project Scaffold & Multi-Agent Memory System
What I Do
- Initialize Project Memory: Create the essential governance and state-tracking files (
gemini.md,AGENT_SYNC.md,progress.md,task_plan.md,findings.md,crash-log.txt,.env.example,.gitignore). - Establish the Constitution: Define core data schemas, behavioral invariants (privacy, offline, security), and the "No Secrets in Code" law before writing application logic.
- Streamline B.L.A.S.T.: Simplify the heavy 5-phase B.L.A.S.T. protocol into an agile 4-stage workflow (Blueprint -> Scaffold -> Execute -> Self-Anneal/Handoff) that works for any tech stack (Android, Web, iOS, Node, Python, Rust, etc.).
- Enable Seamless Multi-Agent Handoffs: Maintain synchronized context so any AI agent can wake up, read
AGENT_SYNC.md, and immediately resume work without asking repetitive questions.
When to Use Me
- When starting a brand-new project or repository.
- When introducing structured agent coordination to an existing codebase that lacks documentation or memory.
- When the user asks: "initialize project memory", "scaffold project", "set up agent sync", or "create files like Floatkit / BLAST".
🏛️ The 7 Essential Files
| File | Role | Purpose |
|---|---|---|
gemini.md |
Project Constitution | Immutable data schemas (JSON shapes), architectural invariants, security rules, and non-negotiables. |
AGENT_SYNC.md |
Agent Coordination Hub | Real-time session task board ([ ], [~], [x]), active branch/phase state, and chronological agent handoff logs. |
progress.md |
Master Product Roadmap | Long-term roadmap broken into numbered phases and milestones with feature completion status. |
task_plan.md |
Active Sprint Blueprint | Immediate sprint plan for the current phase: objectives, architectural guardrails, and granular checklists. |
findings.md |
Research & Discoveries | Institutional knowledge: OS/framework quirks, API gotchas, hardware constraints, and architectural decisions. |
crash-log.txt |
Runtime Triage & Errors | Raw runtime exceptions, crash stack traces, reproduction parameters, and root-cause repair notes. |
.env.example / .gitignore |
Secrets & Hygiene | Credential isolation enforcing the Zero Secrets Law and repository cleanliness. |
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.
- 4d ago First seen · 259 lines · 75 tokens per session scan A 1224691a7850
project-scaffold is a skill published in the GitHub repository Hadi99K/AGENT_SKILLS (3 stars, last pushed 4d ago), licensed MIT. It adds 75 tokens to every session and 2,637 once invoked, about $0.0003 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 2026-10-18.
Other skills, from other repositories
stash
Stash session context [name].
remember
Consolidate stashes + friction into project memory.
continuous-learning-v2
Use when designing a fine-grained, hook-driven learning system that observes every tool call (not just session end), stores atomic "instincts" with confidence scores, and evolves clusters of related instincts into skills, commands, or agents — with project-scoped vs. global separation so React conventions don't leak…
agent-drift-and-re-anchoring
Use when a long-running agent session has drifted from its original goal, when reviewing why an agent kept working on something it wasn't asked to do, when designing checkpoint or re-anchoring behavior for an autonomous/long-horizon agent loop, or when asked about "agent focus", "agent losing the plot", or preventing…
context-engineering
Deliberately curate what an agent sees, when, and how it's structured, to keep output quality high across a session. Use when starting a new coding session, when agent output quality is degrading (hallucinated APIs, ignored conventions), when switching between unrelated parts of a codebase, or when setting up a new…
strategic-compact
Use when deciding whether to manually compact conversation context now versus later — at a phase boundary (research done, plan written, milestone shipped), before switching to an unrelated task, or when responses feel slower/less coherent from context pressure. Trigger phrases include "should I compact now", "context…