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/barateza/mcp-plesk-dev-docs/tlc-spec-drivennpx skills add barateza/mcp-plesk-dev-docs --skill tlc-spec-drivengit clone --depth 1 https://github.com/barateza/mcp-plesk-dev-docsWrote 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/barateza/mcp-plesk-dev-docs/tlc-spec-driven)<a href="https://agentmods.dev/skills/barateza/mcp-plesk-dev-docs/tlc-spec-driven"><img src="https://agentmods.dev/badge/skills/barateza/mcp-plesk-dev-docs/tlc-spec-driven.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 | $0.00148 | $0.01069 |
| Opus 5 | $0.00074 | $0.00535 |
| Sonnet 5 | $0.00030 | $0.00214 |
| Haiku 4.5 | $0.00015 | $0.00107 |
Grade A, and why
tlc-spec-driven 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Lead's Club - Spec-Driven Development
Plan and implement projects with precision. Granular tasks. Clear dependencies. Right tools.
┌──────────┐ ┌──────────┐ ┌─────────┐ ┌───────────────────┐
│ SPECIFY │ → │ DESIGN │ → │ TASKS │ → │ IMPLEMENT+VALIDATE│
└──────────┘ └──────────┘ └─────────┘ └───────────────────┘
Project Structure
.specs/
├── project/
│ ├── PROJECT.md # Vision & goals
│ ├── ROADMAP.md # Features & milestones
│ └── STATE.md # Memory between sessions
├── codebase/ # Brownfield analysis (existing projects)
│ ├── STACK.md
│ ├── ARCHITECTURE.md
│ ├── CONVENTIONS.md
│ ├── STRUCTURE.md
│ ├── TESTING.md
│ └── INTEGRATIONS.md
└── features/ # Feature specifications
└── [feature]/
├── spec.md
├── design.md
└── tasks.md
Workflow
New project:
- Initialize project → PROJECT.md
- Create roadmap → ROADMAP.md
- Specify features → existing workflow
Existing codebase:
- Map codebase → 6 brownfield docs
- Initialize project → PROJECT.md + ROADMAP.md
- Specify features → existing workflow
Context Loading Strategy
Base load (~15k tokens):
- PROJECT.md (if exists)
- ROADMAP.md (when planning/working on features)
- STATE.md (persistent memory)
On-demand load:
- Codebase docs (when working in existing project)
- spec.md (when working on specific feature)
- design.md (when implementing from design)
- tasks.md (when executing tasks)
Never load simultaneously:
- Multiple feature specs
- Multiple architecture docs
- Archived documents
Target: <40k tokens total context Reserve: 160k+ tokens for work, reasoning, outputs Monitoring: Display status when >40k (see context-limits.md)
Commands
Project-level:
| Trigger Pattern | Reference |
|---|---|
| Initialize project, setup project | project-init.md |
| Create roadmap, plan features | roadmap.md |
| Map codebase, analyze existing code | brownfield-mapping.md |
| Record decision, log blocker | state-management.md |
| Pause work, end session | session-handoff.md |
| Resume work, continue | session-handoff.md |
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .skill-meta.json 121 B
- README.md 15 KB
- references/brownfield-mapping.md 7.9 KB
- references/code-analysis.md 2.2 KB
- references/coding-principles.md 1.3 KB
- references/context-limits.md 1.3 KB
- references/design.md 3.3 KB
- references/implement.md 2.0 KB
- references/project-init.md 1.4 KB
- references/roadmap.md 1.4 KB
- references/session-handoff.md 1.3 KB
- references/specify.md 2.8 KB
- references/state-management.md 2.4 KB
- references/tasks.md 5.8 KB
- references/validate.md 2.9 KB
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 · 115 lines · 148 tokens per session scan A 6a5131cbe8bf
tlc-spec-driven is a skill published in the GitHub repository barateza/mcp-plesk-dev-docs (2 stars, last pushed 1mo ago), licensed MIT. It adds 148 tokens to every session and 1,069 once invoked, about $0.0007 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
review-issue
Review an incoming external issue (and any gated-closed PR behind it) and decide whether to assign the contributor or decline. Use when the maintainer says "look at this issue", "review issue.
release
Cut a FastMCP release end to end. Use when the maintainer says "cut a release", "prep a patch", "ship 4.x.y", or asks what a release would contain. Covers the notes preview, the title pun, the docs changelog PR that must land before the tag, the tag itself, the publish fan-out, and verifying gofastmcp.com actually…
review-pr
Monitor and respond to automated PR reviews (Codex bot). Use when pushing a PR, checking review status, or responding to bot feedback. Handles the full cycle of push -> wait for review -> evaluate comments -> fix -> re-push.
fastmcp-client-cli
Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.
reviewing-code
Review code for quality, maintainability, and correctness. Use when reviewing pull requests, evaluating code changes, or providing feedback on implementations. Focuses on API design, patterns, and actionable feedback.
review-security-report
Review FastMCP vulnerability reports before accepting, rejecting, patching, scoring, or publishing them. Use for security advisories, bug-bounty submissions, OAuth or MCP vulnerability claims, and proposed security fixes.