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 zacharygcook/agent-skills --skill ralph-sprintgit clone --depth 1 https://github.com/zacharygcook/agent-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/zacharygcook/agent-skills/ralph-sprint)<a href="https://agentmods.dev/skills/zacharygcook/agent-skills/ralph-sprint"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/ralph-sprint/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/zacharygcook/agent-skills/ralph-sprint"><img src="https://agentmods.dev/badge/skills/zacharygcook/agent-skills/ralph-sprint.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 | $0.00383 |
| Opus 5.5 | $0.00025 | $0.00153 |
| Sonnet 5.5 | $0.00013 | $0.00077 |
| Haiku 4.5 | $0.00006 | $0.00038 |
Grade A, and why
ralph-sprint 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.
What it actually says
Ralph Sprint
Prepare exactly one reviewable sprint and stop before execution.
- Read repository agent instructions, the durable
SPEC.mdor equivalent,.ralph/config.env, and all existing sprint state. - If the current sprint is incomplete or its hooks failed, repair or resume it instead of creating a competing sprint.
- Select the next dependency-ordered slice of the spec. Do not create speculative future sprint folders.
- Create or validate
README.md,IMPLEMENTATION_PLAN.md,relevant-specs.md,chunks.json,prompt.md, andSCRATCHPAD.mdunder.ralph/sprints/<number-name>/. Inprompt.md, refer to every sprint file with its repository-root-relative.ralph/sprints/<number-name>/...path because the harness starts at the repository or orchestration root. - Keep chunks sequential and bounded. Give each concrete acceptance criteria, accurate artifact paths, and repository ownership in multi-repo mode.
- Set
CURRENT_SPRINT, runjust validatewhen available, and repair every setup defect. - Summarize the goal, chunks, validation, risks, and operator review path. Do not run
just run.
When installed beside $ralph-loop, its references/spec-breakdown.md, references/sprint.md, and
references/chunks.md provide the complete shared contract. Preserve those invariants even when the
umbrella skill is unavailable.
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.
- 1mo ago First seen · 29 lines · 63 tokens per session scan A 2d413f71df27
ralph-sprint is a skill published in the GitHub repository zacharygcook/agent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 383 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
cdf-anomalygen
Use when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, quality refinement, and pseudo-labeling — even when the user names only one stage.
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
hsb-ip-packetizer
Choose or explain HSB Sensor RX packetizer fields for HOLOLINKdef.svh. Do not use for full defs, validation, or runtime APB programming.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
parabricks
Plan NVIDIA Parabricks pbrun commands, translate CPU options and check runtime readiness. Use for individual tools, including planning-only questions.