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 artemnovichkov/skills --skill sdlcgit clone --depth 1 https://github.com/artemnovichkov/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/artemnovichkov/skills/sdlc)<a href="https://agentmods.dev/skills/artemnovichkov/skills/sdlc"><img src="https://agentmods.dev/badge/skills/artemnovichkov/skills/sdlc/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/artemnovichkov/skills/sdlc"><img src="https://agentmods.dev/badge/skills/artemnovichkov/skills/sdlc.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 | $0.00085 | $0.01201 |
| Opus 5.5 | $0.00034 | $0.00480 |
| Sonnet 5.5 | $0.00017 | $0.00240 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
sdlc 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sdlc
Turns an idea into shipped, verified code through six stages. Each stage produces one markdown artifact in sdlc/, committed to git. The artifact is the handoff: no stage starts until the previous one's artifact exists and the user has accepted it.
Adapted from Anthropic's AI-Native SDLC Playbook, trimmed for a solo developer. The org-scale layer (separation of duties, policy owners, leading/lagging metrics) lives in references/governance.md and is opt-in.
When to Use
Activate when the user asks to:
- Capture an idea, feature, or bug as a written intent before building
- Turn an intent into a requirements/design spec
- Plan an implementation before writing code
- Set up a verification loop so changes check themselves before review
- Define review policy (
REVIEW.md) or run policy-driven review - Add regression evals for agent configuration (
CLAUDE.md, skills, hooks) - Wire production metrics back into the planning loop
Also activate when a repo already has an sdlc/ directory and the user references an artifact in it.
The Artifact Chain
sdlc/intent/<slug>.md -> what problem, why now, constraints, open questions
sdlc/spec/<slug>.md -> requirements + design, concerns flagged
sdlc/plan/<slug>.md -> files to change, work order, tests required
<diff> + tests -> verified before a human looks
PR + REVIEW.md passes -> reviewed against the spec and plan
production signal -> new sdlc/intent/<slug>.md, loop restarts
One <slug> runs through all three files. That slug is the audit trail — git log sdlc/*/<slug>.md shows the whole decision history for a change.
Commands
| Command | Stage | Produces |
|---|---|---|
/sdlc:init |
setup | sdlc/ scaffold, REVIEW.md, CLAUDE.md sections |
/sdlc:intent |
1. Plan | sdlc/intent/<slug>.md |
/sdlc:spec |
2. Design | sdlc/spec/<slug>.md |
/sdlc:plan |
3. Build | sdlc/plan/<slug>.md |
/sdlc:verify |
4. Test | verification report, optional test-file lock |
/sdlc:evals |
4. Test | evals/ suite + CI workflow |
/sdlc:review |
5. Deploy | REVIEW.md, then delegates to /code-review |
/sdlc:bands |
6. Maintain | sdlc/bands.yaml + watcher script |
What ships with it
22 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.
- .claude-plugin/plugin.json 551 B
- agents/verifier.md 2.0 KB
- commands/bands.md 2.1 KB
- commands/evals.md 2.4 KB
- commands/init.md 2.9 KB
- commands/intent.md 2.0 KB
- commands/plan.md 2.6 KB
- commands/review.md 2.1 KB
- commands/spec.md 2.1 KB
- commands/verify.md 2.5 KB
- hooks/hooks.json 276 B
- hooks/scripts/guard-tests.sh 1.8 KB runs code
- README.md 4.1 KB
- references/governance.md 3.5 KB
- references/stages.md 7.2 KB
- templates/bands.yaml 952 B
- templates/ci/sdlc-evals.yml 1.1 KB
- templates/claude-md-sections.md 985 B
- templates/intent.md 810 B
- templates/plan.md 1.0 KB
- templates/REVIEW.md 1.4 KB
- templates/spec.md 909 B
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.
- 1mo ago First seen · 81 lines · 85 tokens per session scan A 9ba02ac2d85f
sdlc is a skill published in the GitHub repository artemnovichkov/skills (41 stars, last pushed 8d ago), licensed MIT. It adds 85 tokens to every session and 1,201 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 2026-09-07.
Other skills, from other repositories
morning-brief
Operator's read-only morning view of the current GitHub repo in one pass: open counts per queue label, merge-ready PRs, parked decisions with their RECOMMENDED lines, loop-lane telemetry freshness, per CI lane the week's failures by class, limit stops, restarts and turn headroom, and model usage per activity and…
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
kanban-dev-lane
Use when a Hermes Kanban worker wants to run an autonomous implementation delegation lane with a 3-tier fallback chain across claudy -> codex (--yolo) -> agyd (agy --dangerously-skip-permissions) -> Hermes direct on quota exhaustion.
survey
A project-discovery workflow that creates `.claude/context.md`, a shared file describing the project's purpose, design, constraints, and measures of success.
team-diagnosis
Use when the user wants a structured read on their team's health, beyond individual morale. Triggers: "how is my team doing", "I want a team health check", "diagnose my team", "before my skip-level update, what should I flag", "is something off with the team that I'm missing". Reads stakeholder-reflect entries + team…
team-lifecycle
Use when a team is transitioning — forming, storming, norming, performing, adjourning — or resetting after a reorg, new member, or a stuck team. Triggers: "our team is changing", "new team member joining", "team reorg transition", "how do we reset our team", "team dissolving", "adjourning a team". Tuckman's model with…