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 zeeshanhanif/agentic-sdlc-kit --skill sdlc-orchestratorgit clone --depth 1 https://github.com/zeeshanhanif/agentic-sdlc-kitWrote 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/zeeshanhanif/agentic-sdlc-kit/sdlc-orchestrator)<a href="https://agentmods.dev/skills/zeeshanhanif/agentic-sdlc-kit/sdlc-orchestrator"><img src="https://agentmods.dev/badge/skills/zeeshanhanif/agentic-sdlc-kit/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/zeeshanhanif/agentic-sdlc-kit/sdlc-orchestrator"><img src="https://agentmods.dev/badge/skills/zeeshanhanif/agentic-sdlc-kit/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 | $0.00213 | $0.01626 |
| Opus 5 | $0.00106 | $0.00813 |
| Sonnet 5 | $0.00043 | $0.00325 |
| Haiku 4.5 | $0.00021 | $0.00163 |
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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDLC Orchestrator
The loop driver and lifecycle router — deliberately thin. Every stage skill already resolves its own position deterministically, keeps its state on disk, and announces rather than asks; this skill adds only what no single stage owns: the global position, the invocation of the right next stage, and the routing of outcomes between stages. If logic here starts looking like design or build logic, it belongs in a stage skill instead.
Three principles govern it:
- Compute, never store. The global position is derived fresh every time from the artifacts — the plan's sequence joined to each feature's folder state (technical-design.md → designed; ui-design.md → ui-designed; tasks.md fully checked → developer-done; accepted acceptance-report.md → verified). No orchestrator state file, no stored pointers; a brand-new session computes the same position the last one saw.
- Skills stay sovereign. The orchestrator invokes stages and reads their outcomes; it never reaches into a stage's job — never edits tasks.md, never writes an RTM column, never resolves an escalation itself. Human judgment points (amendments, exhausted blocks, design defects) pause the loop and surface — autonomy applies to the mechanical cycle, not to the decisions the pipeline reserved for people.
- Every stop is a resumable state. The loop halts only on the defined stop conditions, each leaving disk truthful (that's the stage skills' discipline, inherited); resuming is just re-running — the computation lands on the same spot.
The loop (default job)
The per-feature cycle, driven in plan-sequence order:
detailed-design → ui-design → feature-implementation → acceptance-verification → next feature.
Run scopes, chosen by the user's ask: one stage ("run the next step"), one feature cycle (the default for "run the next feature" — carry the current front feature from its present stage to verified), or run-until-blocked ("run the loop" — feature after feature until a stop condition or the plan completes). Each invocation announces the computed position before acting ("FEAT-006 is at ui-designed; invoking feature-implementation").
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.
- 9d ago First seen · 137 lines · 213 tokens per session scan A 40753f092fd0
sdlc-orchestrator is a skill published in the GitHub repository zeeshanhanif/agentic-sdlc-kit (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 213 tokens to every session and 1,626 once invoked, about $0.0011 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.