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 drivestream-lab/prayog-skills --skill ground-specgit clone --depth 1 https://github.com/drivestream-lab/prayog-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/drivestream-lab/prayog-skills/ground-spec)<a href="https://agentmods.dev/skills/drivestream-lab/prayog-skills/ground-spec"><img src="https://agentmods.dev/badge/skills/drivestream-lab/prayog-skills/ground-spec/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/drivestream-lab/prayog-skills/ground-spec"><img src="https://agentmods.dev/badge/skills/drivestream-lab/prayog-skills/ground-spec.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 | $0.00089 | $0.02299 |
| Opus 5 | $0.00044 | $0.01149 |
| Sonnet 5 | $0.00018 | $0.00460 |
| Haiku 4.5 | $0.00009 | $0.00230 |
Grade A, and why
ground-spec 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 11d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ground spec
Validate implementation against the product spec REQs assigned to this
completed wave (plan / WorkManifest TASK implements lists) and actual
repo artifacts — not every future REQ in the full product spec, and not PRD
text alone. Produce a Ground Report that the next wave's /pre-implement
consumes as a contract baseline.
Content skills write locally and emit Forge readiness; they do not commit, push, branch, open PRs, label, create issues, or merge.
Canonical artifact:
{reports_dir}/Ground-Report-{SPEC}-W{N}.md
(prayog-skills/references/artifact-write-contract.md).
Checks: references/checks.md (G1–G10).
Ids: prayog-skills/references/id-conventions.md (GF-* for findings).
NON-NEGOTIABLE
- Resolve paths from
.harness/profile.yamlor references/layout-defaults.md. Includetests/**in scope when mapping evidence. - Run the repo's automated ground check when
{ground_command}is defined in the harness profile. Include full output in the report. If{ground_command}is not defined, perform manual REQ validation by readingsource_rootsandtests/**directly. - Check every
REQ-*assigned to this wave via plan / WorkManifest TASK rows — map each to a verifiable artifact (test result, entry point, module boundary, verify script output). Do not require coverage of REQs owned only by future waves. Use engineering terms: "entry point", "module boundary", "output shape" — not language-specific terms. - Consume approved plan/manifest intent plus actual loop/unit evidence
and human accept (
Wave-Execution-*, unit results,wave-accepted/ wave-acceptance). Optional/legacyLive-Verify-*is not required. Cite layers separately. - Check cross-spec contracts: modules from this wave may only consume interfaces from prior waves as documented in those waves' Ground Reports.
- Check boundary rules per ADRs and domain-filtered MDC rules (G5/G6).
- Do not mark spec
human_approved— already set atwave-acceptance(only approval signal). This skill prepares the merge package forwave-signoff(merge/publish only). - Populate the Contracts Produced section — structured handoff for
/pre-implementof the next wave. Without it, the chain is broken. - Cite learning ids — when
{reports_dir}/Learning-Extract-{initiative}-W{N}.mdexists, add a Learning cited table ofL-*ids (do not re-author learning SSOT). - Discrepancy / blocker ids use stable
GF-*— citeREQ-*in the row, not as the blocker primary key. Do not reuse feasibilityFF-*. - Write Ground Report and as-built updates locally; prepare the
exact-head merge package for
wave-signoff; pin routes towave-done-actionthenwave-signoff(merge only). Never commit or merge from this skill. As-built writes follow the split inprayog-skills/references/artifact-write-contract.md—Implementation-Status-{INIT}.mdfor detail, one index row inimplementation-status.mdfor the pointer; never append a new table to the shared index. - If a codegraph provider is available (MCP tool matching
prayog-skills/references/codegraph-tool-contract.md, or a local CLI), prefer it for cross-spec contract / boundary questions. Always fall back to directsource_rootsreads when unavailable — never block or change outcome selection on its absence.
What ships with it
7 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.
- 11d ago First seen · 179 lines · 89 tokens per session scan A bca3b4bd3724
ground-spec is a skill published in the GitHub repository drivestream-lab/prayog-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 2,299 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.