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 ashermahonin/agentic-skills --skill sdlc-orchestratorgit clone --depth 1 https://github.com/ashermahonin/agentic-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/ashermahonin/agentic-skills/sdlc-orchestrator)<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/sdlc-orchestrator"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/sdlc-orchestrator/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/ashermahonin/agentic-skills/sdlc-orchestrator"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/sdlc-orchestrator.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 | $0.00063 | $0.00605 |
| Opus 5.5 | $0.00025 | $0.00242 |
| Sonnet 5.5 | $0.00013 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
sdlc-orchestrator 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 2mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDLC orchestrator
Purpose
Choose the route, keep ownership clear, and stop a broad request from turning into an unbounded chain of skills.
Inputs
- Restate the desired outcome in one sentence.
- Read the repository state and relevant project memory.
- Classify the task as a new product, existing-product change, narrow change, release, incident, review, documentation update, or agent-system task.
- Identify the first decision that could invalidate later work.
- Check that the runtime can read, write, execute, validate, and request approval as the route requires.
Decision process
- Select the smallest entrypoint in the installed route map. When no route map is exposed, use the phase and entrypoint guidance in the reference.
- Record the route, why it fits, what it deliberately excludes, and when it must stop.
- Run only the discovery and planning steps needed to resolve real uncertainty.
- Freeze affected behavior, interfaces, platform constraints, and acceptance criteria before decomposition.
- Give parallel workers disjoint ownership and define their merge order before delegation.
- For production code, route through
tdd-workflow,engineering-quality, andservice-implementationas the task requires. - Match validation depth to the blast radius. Add security, compliance, performance, and release checks only when the affected surface calls for them.
- Update the canonical documentation and project memory with decisions future work needs.
Decision boundaries
- A route defines ownership and order; it does not grant permission.
- Keep read-only analysis separate from write-authorized implementation.
- Verify current external behavior through primary documentation, preferably Context7 MCP where available.
- Ask for approval immediately before irreversible, production-facing, costly, or security-sensitive actions.
- Stop when missing user intent or unavailable evidence would materially change the result.
Decision record
- Selected route and rejected broader alternatives
- Decision, permission, and stop boundaries
- Artifact ownership and merge order for parallel work
- Validation, rollback, and completion evidence
- Final handoff with documentation links
What ships with it
2 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.
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.
- 2mo ago First seen · 62 lines · 63 tokens per session scan A e0dab64c6459
sdlc-orchestrator is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 605 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 2026-08-31.
sdlc-orchestrator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sdlc-orchestratorashermahonin/agentic-skills | Skill | 10 | 2mo ago | MIT | A | 63 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |