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 pre-implementgit 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/pre-implement)<a href="https://agentmods.dev/skills/drivestream-lab/prayog-skills/pre-implement"><img src="https://agentmods.dev/badge/skills/drivestream-lab/prayog-skills/pre-implement/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/pre-implement"><img src="https://agentmods.dev/badge/skills/drivestream-lab/prayog-skills/pre-implement.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 | $0.00081 | $0.03165 |
| Opus 5 | $0.00041 | $0.01582 |
| Sonnet 5 | $0.00016 | $0.00633 |
| Haiku 4.5 | $0.00008 | $0.00316 |
Grade A, and why
pre-implement 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 yesterday.
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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-implement
Produce the pre-flight checklist for one wave slice. This skill is
gate-only: it never opens a branch and never implements product code —
even if the user asks after the checklist. Implementation belongs to
/loop-spec. 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}/Pre-Implement-{INIT}-W{N}.md
(prayog-skills/references/artifact-write-contract.md).
NON-NEGOTIABLE
- Resolve paths from
.harness/profile.yamlwhen present; else references/layout-defaults.md. - Gate check first — before reading anything else, confirm the prior
wave's Ground Report exists and its as-built row is
human_approved(set at priorwave-acceptance, not at signoff). If not: stop and state which gate is unsatisfied. Do not produce a checklist for a wave whose predecessor is not approved. - Read
rules_globper the domain-filter approach in references/governance.md — not all files. - Read relevant ADRs (keyword-match, then deep-read matched Accepted ADRs).
- Never implement product code and never open/create a branch. Output the checklist (+ Forge readiness when board/branch readiness is absent).
- Cite concrete file paths for this repo and slice.
- Describe contracts in engineering terms — entry points, input/output shapes, invariants. Do not use language-specific syntax.
- Verify spend freshness: product-spec H1–H3 citations (and G2 spec merge when applicable) still match live durable roots; board wave issue exists for this W{N}. Stop on authority drift. Do not require Implementation-Plan source-freshness / plan-file digest as long-term SSOT (plan is walk-time; may be purged at initiative closure).
- Resolve
check_commandandtest_command. Resolveverify_commandas the live script underlive_verify_dirwhen the wave plan triggers P15 (new/material product surface) — FAIL the gate on bare N/A or unit-only (make test/{test_command}). When live is applicable, require journey/capability-shaped intent:coversincludeCAP-{nn}and/orJ-{nn}, non-emptyfixturesunderfixtures_dir, andhuman_observationswhen opaque. Resolveground_commandwhen applicable. If the plan/profile/AGENTS.md/tests_readmecannot supply a required command, stop with MISSING command. The human runs{verify_command}(+ look-ats) at checkpointwave-acceptance; this skill does not execute it. Layer policy: references/live-smoke-policy.md. Human accept ingress is GitHub labelwave-accepted(skills never apply it; ack includes look-ats when declared). - WorkManifest spend authority — prefer the board wave/EPIC issues
seeded from plan §9 as long-term intent (see
prayog-skills/references/workmanifest-contract.md). WhenImplementation-Plan-{initiative}.mdis still on the tree, validate §9 withscripts/workmanifest_contract.py/validate_workmanifestand fail closed on contract / incomplete TASK exit / P15 live gaps as today. When the plan file is already gone (post–initiative-closure purge is initiative-end only — during waves the plan should still exist), reconstruct TASK/REQ/exit/live intent from board issue bodies projected at seed plus product-spec REQs — do not invent ids. Board text is projection of the approved manifest, not a second libre authority. - Confirm board seed: EPIC issue exists, every declared wave
issue exists, and waves are sub-issues of the EPIC on the programme
board (governance
project_board.name). Board/branch/PR state is read-only. If seed or bound wave head is missing/partial: stop, emit Forge / external-action readiness (e.g. recommend/create-board-ticketsor wave-head binding) — do not invoke mutation from this skill. - Spec merge gate — before W0 (and before any
/loop-spec), confirm:- bound wave head context is the integration branch (
develop) or afeature/INIT-*-w{N}-*wave branch cut from it — not an openchore/*-spec-*Draft spec PR branch (wave head is bound by Forge/human context — this skill does not open it); - product spec
INIT-*.mdwith H1–H3 citations exists on the integration branch; prefer also verifying mergedImplementation-Plan-{initiative}.mdwhen still present (spec PR merge / G2); - the merged spec PR head carried
spec-lgtm(verify viagh pr viewon the closed spec PR: label present andmergeCommit/headRefOidmatches attestation or Approvecommit_id); - board tickets seeded (wave issues exist per rule 11). If any check fails: stop — do not produce a pass checklist or write product code.
- bound wave head context is the integration branch (
- If a codegraph provider is available (MCP tool matching
prayog-skills/references/codegraph-tool-contract.md, or a local CLI), prefer it for impact/dependency questions when reading contracts consumed. Always fall back to directsource_rootsreads when unavailable — never block or change outcome selection on its absence.
What ships with it
8 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.
- yesterday Changed · +4 lines 8948d8f3f24e
- 8d ago First seen · 207 lines · 81 tokens per session scan A 513cc810a065
pre-implement is a skill published in the GitHub repository drivestream-lab/prayog-skills (2 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 3,165 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…