compounding

A session review tool for finding ways to improve an AI assistant named acai. It examines the session, logs, and source files for repeated errors, confusing tools, and missing capabilities.

In plain words
What is it for?
Use it at the end of a session to review errors, inspect current logs, and identify opportunities for new tools, clearer instructions, or better workflows.
Why use it?
It turns recurring mistakes and workflow problems into concrete ideas for improving the assistant and its tools.

Skill for Claude CodeCodex

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/travisennis/acai/compounding
Any agent
npx skills add travisennis/acai --skill compounding
Clone the repo
git clone --depth 1 https://github.com/travisennis/acai

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 551 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 $0.00018 $0.00551
Opus 5 $0.00009 $0.00275
Sonnet 5 $0.00004 $0.00110
Haiku 4.5 $0.00002 $0.00055

Measured 2d ago against content hash 0bbb5daaf22e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compounding 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 2d 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.

.agents/skills/compounding/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compounding Skill

Analyzes the current session to identify self-improvement opportunities for acai.

When to Use

Invoke this skill at the end of a session when:

  • The session revealed gaps in acai's knowledge or capabilities
  • Tool descriptions caused confusion or misuse
  • Repeated patterns suggest a new tool or workflow would help
  • Errors occurred that indicate systemic issues

Analysis Process

1. Session Analysis

Review the current session messages in context for patterns indicating improvement opportunities:

  • System prompt gaps: Missing context, unclear instructions, assumptions that failed
  • Tool description issues: Unclear parameters, missing edge cases, confusing descriptions
  • Repeated tool patterns: Same tool sequences used repeatedly (potential new tool)
  • Error patterns: Tool failures, retries, or workarounds

2. Log Analysis

Read ~/.acai/logs/current.log using the Read tool to identify error patterns:

  1. Filter for error indicators: Error, Exception, Failed, warn
  2. Cross-reference errors with session tool calls
  3. Distinguish systemic issues from one-off errors

3. Source File Analysis

Cross-reference findings with source files:

  • System prompt: source/prompts.ts - core prompt components
  • Tool descriptions: source/tools/*.ts - each tool has a description string

Output Format

Present findings as a structured report:

## Session Improvement Analysis

### System Prompt Gaps
- [finding 1]
- [finding 2]

### Tool Description Issues
- [finding 1]
- [finding 2]

### Potential New Tools/Capabilities
- [finding 1]

### Error Patterns (from logs)
- [finding 1]

User Selection

After presenting findings, ask the user to select which improvements to accept:

  1. Number each finding
  2. Present as a selection menu
  3. User responds with numbers (e.g., "1, 3, 5")

Writing Improvements

For accepted findings, write to improvements.md in the project root:

# Improvement Recommendations

## System Prompt
- [accepted finding with context]

## Tool Descriptions
- [accepted finding with specific tool and suggested change]

## New Capabilities
- [accepted finding with rationale]

Read the full file on GitHub · 97 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. 2d ago First seen · 97 lines · 18 tokens per session scan A 0bbb5daaf22e

Subscribe to this mod's changes

compounding is a skill published in the GitHub repository travisennis/acai (5 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 551 once invoked, about $0.0001 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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