compounding-preflight

compounding-preflight is a skill for Claude Code, Codex from jtsternberg/claude-plugins. It costs 78 tokens per session (635 once invoked), scanned A, original, MIT.

A change-set check against a project's docs/compounding.md ledger, which records lessons and rules from earlier work. It checks both whether a change breaks an existing rule and whether it reveals a new one.

In plain words
What is it for?
Use it to inspect a Git diff, report violated rules with file locations, check related open beads, and suggest new entries for the ledger.
Why use it?
It catches known mistakes before review, pull-request creation, or release, while also preserving useful lessons for future changes.

Skill for Claude CodeCodex

Part of the jtsternberg plugin — 6 skills, 31 plugins shipped together

Install

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.

agentmods
npx agentmods add skills/jtsternberg/claude-plugins/compounding-preflight
Any agent
npx skills add jtsternberg/claude-plugins --skill compounding-preflight
Clone the repo
git clone --depth 1 https://github.com/jtsternberg/claude-plugins

Made for: Claude Code, Codex.

Or install jtsternberg, the plugin that ships this one along with the rest of its 6 skills, 31 plugins.

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 compounding-preflight

README.md
[![agentmods](https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/compounding-preflight.svg)](https://agentmods.dev/skills/jtsternberg/claude-plugins/compounding-preflight)
Your own site
<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/compounding-preflight"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/compounding-preflight.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 635 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00078 $0.00635
Opus 5 $0.00039 $0.00318
Sonnet 5 $0.00016 $0.00127
Haiku 4.5 $0.00008 $0.00064

Measured yesterday against content hash cda279778fe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compounding-preflight 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.

.claude/skills/compounding-preflight/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compounding Preflight

Diff-check a change-set against the ledger at docs/compounding.md, both directions: does the change violate an entry, and does it teach one?

Steps

  1. Resolve the change-set. Default git diff main...HEAD (or the staged/working diff if no branch delta); a PR number or explicit range wins when given.

  2. Read docs/compounding.md in full — the bold headlines are the rules; the Known False Positives section is the list of things to NOT report.

  3. Scan the diff against each headline. For docs/skills rules, include changed *.md files AND script headers/--help text. Cheap greps first (the phrases and patterns entries name), judgment second.

  4. Report violations as rule headline → file:line → one-line fix, most severe first. Anything matching a Known False Positive is not a finding.

  5. Tripwire scan. Parked beads declare where their knowledge bites via a tripwire-paths: line. Run the shared matcher — the same engine the distributed beads-workflow:tripwire-scan skill and its PostToolUse hook use — against the change-set:

    bash plugins/beads-workflow/scripts/tripwire-match.sh scan
    

    Report each hit (bead id → matched file → the bead's one-line why) so the author acts on it, consciously defers, or closes the bead as satisfied. Pass a range/commit to scan a specific delta; add --json for machine output. The matcher handles anchor precision (comment / string / git-ref-pinned range) and self-trip suppression (in_progress beads self-suppress) — no hand-grepping.

  6. Propose compounding. If the change-set fixed a bug class, absorbed a review correction, or removed accreted text, draft the entry (headline + ≤3 sentences + provenance) and ask whether to add it — the write gate at the top of the doc decides format; a one-time incident does not qualify.

  7. Prune check. Name any existing entry this change-set made obsolete or turned into a mechanical guard (then the entry's catch text becomes a pointer to the guard, or the entry is deleted).

Read the full file on GitHub · 45 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. yesterday Changed · +8 lines cda279778fe5
  2. 5d ago First seen · 37 lines · 78 tokens per session scan A f63cc0aeea03

Subscribe to this mod's changes

compounding-preflight is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 635 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.

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

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

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens