recheck-against-upstream-deep

recheck-against-upstream-deep is a skill for Claude Code from melodic-software/claude-code-plugins. It costs 103 tokens per session (1,279 once invoked), scanned A, original, MIT.

A large-scale documentation review process that compares an entire subsystem or repository with its current official upstream documentation.

In plain words
What is it for?
Use it to check broad framework, integration, or subsystem usage and record missing, intentional, or undocumented differences.
Why use it?
It helps uncover differences between local code or settings and the software's current documented behavior.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the discipline plugin — 18 skills shipped together

Good fit Use it to check broad framework, integration, or subsystem usage and record missing, intentional, or undocumented differences.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add melodic-software/claude-code-plugins
Claude Code
/plugin install discipline

Made for: Claude Code.

Or install discipline, the plugin that ships this one along with the rest of its 18 skills.

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 recheck-against-upstream-deep

README.md
[![agentmods](https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/recheck-against-upstream-deep/github.svg)](https://agentmods.dev/skills/melodic-software/claude-code-plugins/recheck-against-upstream-deep)
Your own site
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/recheck-against-upstream-deep"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/recheck-against-upstream-deep/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 recheck-against-upstream-deep

Your own site · 80×15
<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/recheck-against-upstream-deep"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/recheck-against-upstream-deep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,279 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.
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 $0.00103 $0.01279
Opus 5.5 $0.00041 $0.00512
Sonnet 5.5 $0.00021 $0.00256
Haiku 4.5 $0.00010 $0.00128

Measured 12d ago against content hash 7b9887cdbf83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

recheck-against-upstream-deep 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 12d 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.

plugins/discipline/skills/recheck-against-upstream-deep/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recheck against upstream. Deep

The fan-out tier of the sibling /discipline:recheck-against-upstream. Same upstream-conformance discipline; heavier execution. Where the base skill rechecks the one surface in play inline, this one fans fresh-context subagents out over a whole subsystem, framework, or repo, doc-by-doc, the execution tier the base skill's context cannot cover from within itself.

The shared method. Re-anchor, audit, correct forward, report, and the tone that firing this is not an accusation, lives in ${CLAUDE_PLUGIN_ROOT}/context/re-anchor-audit-correct.md. The discipline this re-anchors, its portable baseline, and the three divergence categories (gap / deliberate / undocumented) live in the sibling recheck-against-upstream. Read both; this file adds only the fan-out delta. There is no separate copy of the discipline or the taxonomy here. Update the sibling and this tier follows.

When this tier, not the inline recheck

Reserve the fan-out for when the upstream surface area is broad enough to justify the subagent cost: a whole framework's configuration, an entire integration's API usage, a subsystem that leans on many upstream contracts at once. For a single surface or a short session, the inline recheck in the sibling is the right tool; this tier is overkill.

The fan-out

Run this in place of the sibling's inline audit and correct-forward steps:

  1. Enumerate the surfaces. List every upstream-dependent surface in the subsystem/repo under review. Each config block, API call site, infra definition, and documented contract the work rests on. Do not spot-check one.
  2. Fan out, throttled, doc-by-doc. Dispatch per ${CLAUDE_PLUGIN_ROOT}/context/fan-out.md: blind fresh-context subagents, bounded waves, failed-subset retry. Each subagent fetches the CURRENT official upstream docs for its surface and classifies the divergence per the sibling's three categories. Each subagent reads every docs page through the shared docs lookup, following ${CLAUDE_PLUGIN_ROOT}/reference/docs-lookup-procedure.md with <scripts> = ${CLAUDE_PLUGIN_ROOT}/scripts; resolve both to absolute paths in the brief, since a subagent's shell does not expand the plugin variable. The subagent runs bash "<scripts>/fetch-docs.sh" --cache --profile <profile> --out "$out" <slug-or-url> as the procedure's step 1 gives it. The read that settles a verdict follows the procedure's step 6: re-fetch with --max-age 0, so a cached copy never stands in for the current docs, and read raw bytes. A source that is not a docs page keeps its existing route.
  3. Checkpoint the partial ledger mid-run, if a durable slice exists. So a crash mid-fan-out does not lose completed waves, checkpoint the partial ledger to the session's durable topic-memory slice when one is available; where the session has no such durable store, proceed without it rather than asserting a persistence surface. This is the only persistence this tier performs. Nothing is mandatory beyond it.
  4. Merge and report an inline divergence ledger. One list keyed by surface: its category (gap / deliberate / undocumented) and the current upstream source that resolved it. Correct gaps toward upstream this turn; re-check that deliberate divergences still hold and flag any the docs have overtaken; surface undocumented ones for the human with both options.

Read the full file on GitHub · 93 lines

Files

What ships with it

1 file 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.

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. 12d ago Changed · +10 lines 7b9887cdbf83
  2. 22d ago Changed · -20 tokens per session 61ad2ca6b577
  3. 1mo ago Changed · -16 lines edb148f8b3f4
  4. 1mo ago First seen · 99 lines · 123 tokens per session scan A 243588dd1252

Subscribe to this mod's changes

recheck-against-upstream-deep is a skill published in the GitHub repository melodic-software/claude-code-plugins (26 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 1,279 once invoked, about $0.0004 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 2026-09-03.

Related

Other skills, from other repositories

refactor-decompose-function

For long functions: break into smaller pieces, extract helper functions, reduce nesting, improve testability and readability.

jimmc414/claude-code-plugin-marketplace · 28 tokens

pr-analyzing

Use this skill when the user asks to analyze a specific GitHub pull request, review a PR's architectural impact, assess what changed in a PR and why it matters, or research the code relationships affected by a PR — example triggers like "analyze PR.

shopwareLabs/ai-coding-tools · 56 tokens

catch-expected-errors

For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.

jimmc414/claude-code-plugin-marketplace · 24 tokens

find-shortest-path

For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A problems.

jimmc414/claude-code-plugin-marketplace · 37 tokens

visual-design-system

World-class visual design system standards — OKLCH color science, fluid typography, elevation hierarchy, branded asymmetric corners, and dark mode implementation.

systempromptio/systemprompt-marketplace · 31 tokens

css-coding-standards

CSS coding standards for systemprompt.io — one --sp- token system in OKLCH with color-mix derivation, BEM naming, one component per file, CSS-first behaviour, forbidden constructs, comment rules, and file limits. Canonical source of truth for all CSS. Load before writing or reviewing any stylesheet.

systempromptio/systemprompt-marketplace · 72 tokens