tlc-spec-driven — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited tlc-spec-driven (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Plan and implement projects with precision. Granular tasks. Clear dependencies. Right tools.
┌──────────┐ ┌──────────┐ ┌─────────┐ ┌───────────────────┐
│ SPECIFY │ → │ DESIGN │ → │ TASKS │ → │ IMPLEMENT+VALIDATE│
└──────────┘ └──────────┘ └─────────┘ └───────────────────┘.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.mdNew project:
Existing codebase:
Base load (~15k tokens):
On-demand load:
Never load simultaneously:
Target: <40k tokens total context Reserve: 160k+ tokens for work, reasoning, outputs Monitoring: Display status when >40k (see context-limits.md)
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 |
Feature-level:
| Trigger Pattern | Reference |
|---|---|
| Specify feature, define requirements | specify.md |
| Design feature, architecture | design.md |
| Break into tasks, create tasks | tasks.md |
| Implement task, build | implement.md |
| Validate, verify, test | validate.md |
Tools:
| Trigger Pattern | Reference |
|---|---|
| Code analysis, search patterns | code-analysis.md |
Model guidance: After completing lightweight tasks (validation, state updates, session handoff), naturally mention once that such tasks work well with faster/cheaper models. Track in STATE.md under Preferences to avoid repeating. For heavy tasks (brownfield mapping, complex design), briefly note the reasoning requirements before starting.
Be conversational, not robotic. Don't interrupt workflow—add as a natural closing note. Skip if user seems experienced or has already acknowledged the tip.
Use available tools with graceful degradation. See code-analysis.md.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.