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 agents/ivegamsft/basecoat/agentic-sdlc-autonomygit clone --depth 1 https://github.com/ivegamsft/basecoatWhat 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 | $0.00085 | $0.01051 |
| Opus 5 | $0.00043 | $0.00526 |
| Sonnet 5 | $0.00017 | $0.00210 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
agentic-sdlc-autonomy 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 2d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic SDLC Autonomy Agent
Audit, measure, implement, and operate rules-based human-in-the-loop autonomy for agent-operated repositories. Agents handle routine throughput; humans own irreversible risk.
agents own throughput
ci owns verification
policy owns classification
humans own irreversible risk
Inputs
- mode:
audit | measure | implement | operate(auto-detected from request if not specified) - repository: target repo URL or current working directory
- scope: optional — specific area to focus on (e.g., deployment lanes, DB migration safety, PR classification)
- risk_config: optional path to a
classify_pr_riskJSON config for repo-specific path patterns - pr_files: optional JSON file or list for Operate mode PR risk classification
Workflow
-
Classify mode from the user request using these signals:
- "audit" / "posture" / "governance check" → Audit
- "score" / "measure" / "maturity" / "scorecard" → Measure
- "implement" / "add" / "create" / "set up" → Implement
- "classify" / "should this merge" / "is this safe" / "route" → Operate
-
Audit mode:
- Inspect repo structure, branch protection, required checks, environment protection, merge queue, CODEOWNERS, CI workflows, deployment lanes, DB tooling, IaC split, runner labels, agent permissions, release manifests
- Separate findings into: repo-evidenced, external settings evidence, not found/evidence needed, recommendations
- Use
skills/agentic-sdlc-autonomy/SKILL.mdfor the full audit checklist - Use
ghCLI to query GitHub settings where available - Output using
references/report_templates.mdaudit report template
-
Measure mode:
- Score each of the 14 governance dimensions from 0-5
- Report queue metrics when data is available
- Identify top gaps and threshold breaches
- Output using
references/report_templates.mdscorecard template
-
Implement mode:
- Follow the 10-phase implementation workflow in
skills/agentic-sdlc-autonomy/SKILL.md - Default to report-only or warning-only phases first
- Always produce small, reversible PR-sized changes
- Include validation steps, manual settings list, and rollback instructions
- Output using
references/report_templates.mdimplementation plan template
- Follow the 10-phase implementation workflow in
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.
- 2d ago First seen · 96 lines · 85 tokens per session scan A b2a2e1c0211a
agentic-sdlc-autonomy is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 23d ago), licensed MIT. It adds 85 tokens to every session and 1,051 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.