Skip to content

MiniMax-AI/mcode-stack / stacks/ronny/skills/context-tax-audit

context-tax-audit

Unverified

Inventory everything an agent injects into each request besides the user's message, such as system prompt, environment info, skill list, tool definitions, per-turn context blocks and reminders, and check necessity, frequency, precision, position and prompt-cache impact. Use when reviewing an agent's prompt assembly, chasing low cache hit rates, or trimming per-turn overhead.

Context Tax Audit

Every request carries more than the user's sentence: system prompt, environment info, the skill list, tool definitions, per-turn context blocks, reminders. Most of it is worth paying for. The audit finds what is not, and what is placed so that it breaks the prompt cache.

Companion to MCode Engineering Notes 05 (how the agent learns the current time — and why stuffing date into the system prompt breaks the prefix cache). Plain-text checklist: checklists/context-tax.md.

1. Inventory one real request

Capture an actual request the agent sends (debug log, proxy, or the code that assembles it). List every part except the user's message:

PartWhere it sitsHow often it changesTokens

Count tokens with a tokenizer and name it; treat the counts as relative. Do a fresh-session first request and a later turn, since they often differ.

2. Necessity - what breaks if you delete it?

For each part, write one sentence: "without this, the model would ...". Typical answers: without environment info it guesses the OS and shell; without the current time it assumes its training year; without a time budget it does not wrap up before a deadline. If you cannot write the sentence, the part is a candidate for removal.

3. Prompt-cache placement

Caches match on prefix. One changed byte invalidates everything after it.

  1. Content that is at the front and changes every request is the most expensive. Move it later.
  2. Content written into history and never edited costs once and then stays cacheable.
  3. Content attached only to the current request is never cached and is paid at full price every time. Control its frequency.

Rules of thumb:

  • Stable first, volatile last. Keep # Environment free of current time; put time in per-turn <agent-context> (or the equivalent user-message block).
  • Never rewrite reminders already in history; change only future turns.
  • Use only the precision you need. A timestamp to the second guarantees every copy differs once placement is already right.
  • Request-only reminders never enter the cache — control how often they fire, but do not confuse that thrift with protecting the prefix.

4. Run the checklist

ItemQuestion
Prefix awarenessCan you point to the stable prefix vs what changes every turn?
NecessityFor each part, where does the model go wrong without it?
PositionIs anything volatile inside the system prompt or tool definitions? (e.g. time in # Environment)
FrequencyDoes a changing field need every turn / request, or only at the start, key points, or on change?
PrecisionDoes it need seconds, exact counts? Higher precision means more turn-to-turn variation.
HistoryAre reminders already in history ever rewritten later?
Recovery pathsIf you remove something, does it vanish entirely on compaction, session resume or subagents? Who restores it?
MeasurementBefore and after a change, do you look at cache hit rate, cost per turn and task quality, not just token count?

Output

The inventory table, a list of parts to cut, move, reduce in frequency or reduce in precision (each with the reason), and what to measure to confirm the change helped.

rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 192kUpdated Claude CodeCodexVerifiedInstall