sparq: Skill for Claude Code

.claude/skills/proceed-and-document/SKILL.md

proceed-and-document is a skill for Claude Code from sparq-org/sparq. It costs 152 tokens per session (1,469 once invoked), scanned A, original, MIT.

A procedure for making a design choice when work is blocked only because a maintainer has not approved one yet. The agent records the choice and continues.

In plain words
What is it for?
Use it when an agent must choose between reasonable design options during a task. It does not cover missing credentials, access problems, or truthfulness checks.
Why use it?
It avoids pausing every task for a routine judgment call while leaving a clear record for later review.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions AGENTS.md.

This is sparq-org/sparq's own configuration. It tells Claude Code how to work on sparq itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sparq configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is wording lives in [`AGENTS.md`](../../../AGENTS.md) → *"STANDING RULE — proceed.

Part of the sparq plugin — 55 skills, 20 agents, 2 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to sparq-org/sparq. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sparq-org/sparq/main/.claude/skills/proceed-and-document/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sparq-org/sparq

Made for: Claude Code.

Or install sparq, the plugin that ships this one along with the rest of its 55 skills, 20 agents, 2 hooks.

Wrote 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.

agentmods badge for proceed-and-document

README.md
[![agentmods](https://agentmods.dev/badge/skills/sparq-org/sparq/proceed-and-document/github.svg)](https://agentmods.dev/skills/sparq-org/sparq/proceed-and-document)
Your own site
<a href="https://agentmods.dev/skills/sparq-org/sparq/proceed-and-document"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/proceed-and-document/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.

agentmods 80×15 button for proceed-and-document

Your own site · 80×15
<a href="https://agentmods.dev/skills/sparq-org/sparq/proceed-and-document"><img src="https://agentmods.dev/badge/skills/sparq-org/sparq/proceed-and-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.01469
Opus 5 $0.00076 $0.00734
Sonnet 5 $0.00030 $0.00294
Haiku 4.5 $0.00015 $0.00147

Measured 9d ago against content hash 1e8073e46178, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

proceed-and-document 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.

.claude/skills/proceed-and-document/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

proceed-and-document — proceed on a decision, document it, steer post-hoc

[OPUS-4.8] Internal agent skill. Authored by Opus 4.8 (Fable unavailable — flag for re-review when Fable returns). This skill is the reusable, single-source form of the standing rule that was previously trapped as inline prompt prose inside .claude/workflows/autonomous-scheduler.js. Design basis: research/agent-effectiveness-program.md §2.3 (the hook/workflow/skill/slash/cron granularity rule — a single-agent procedure needing judgment each run is a SKILL) and §7 Phase 1.5.1. Coordinates with bead sq-6psmk (the durable commit of the proceed-on-decision update to the scheduler).

This skill does NOT define the rule — it carries it. The authoritative wording lives in AGENTS.md"STANDING RULE — proceed without waiting for the maintainer's greenlight". This file is the agent-facing procedure that both the workflow strings and a hand-dispatched agent point at by name so the rule is inherited identically everywhere instead of re-typed (and silently drifting) per brief. If the two ever disagree, AGENTS.md wins; fix this file to match.

When this fires

You are working a bead (in the autonomous scheduler or hand-dispatched) and you reach a point where you would normally stop and ask the maintainer:

  • the bead needs a design greenlight you don't have, or
  • there is a decision (a default value, an API shape, a naming choice, a scope cut) you would otherwise raise.

That is not a blocker. Proceed.

What to do (the four steps)

  1. Make the best-judgment choice. Pick the option a careful maintainer would most likely accept; prefer the smallest reversible version (opt-in / feature-gated / additive) so a later correction is cheap. Do not gold-plate.
  2. Document the choice in the PR body — a short "Decision: chose X over Y because Z; reversible via …" note, so the diff is reviewable as a decision, not just code.
  3. Leave a one-line bead note recording the same choice (bd note <id> "…"), so the decision is discoverable from the task, not only the PR.
  4. Open a short GitHub issue flagging the decision for the maintainer to steer later. Lead it with the 🤖 SPARQ-agent self-id blockquote (see below), name the bead + PR, state the default you chose in one line, and ask the one question you'd have asked. This converts "needs-user / awaiting greenlight" into "proceeded with default X — see issue #N."

Read the full file on GitHub · 104 lines

Changes

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.

  1. 9d ago First seen · 104 lines · 152 tokens per session scan A 1e8073e46178

Subscribe to this mod's changes

proceed-and-document is a skill published in the GitHub repository sparq-org/sparq (10 stars, last pushed yesterday), licensed MIT. It adds 152 tokens to every session and 1,469 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens