AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
MCP verified MIT Self-run

Codex Hygiene

mcp-sunflower-of-parchman-codex-hygiene · by sunflower-of-parchman

Codex skill for auditing and tuning Codex Desktop context/tool surfaces

↗ Repository
— No reviews yet
0 installs
37 views
0.0% view→install

Install

$ agentstack add mcp-sunflower-of-parchman-codex-hygiene

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ● Environment & secrets Used
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/mcp-sunflower-of-parchman-codex-hygiene)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude DesktopCursorWindsurf

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Codex Hygiene? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Codex Hygiene

A small Codex skill for auditing and tuning Codex Desktop context and tool surfaces.

Use it to measure recent Codex Desktop telemetry, review MCP/app/skill availability, and keep long-running goal workflows scoped to the current work.

Community skill for local Codex setup hygiene.

What It Does

  • Measures recent Codex Desktop tool-list and per-thread token telemetry with read-only SQLite queries.
  • Helps identify whether elevated usage correlates with app surface size, MCP/plugin state, snapshot reuse, stale project stanzas, long-thread replay, or background fan-out.
  • Distinguishes actual tool calls from tool availability, enabled state from cached inventory, and thread-local token changes from mixed-thread totals.
  • Suggests reversible hygiene steps instead of deleting logs, caches, or projects.
  • Keeps long-running goal work quality-aware: narrow replay and tool scope without blindly lowering reasoning, banning subagents, or avoiding real source evidence.

Install

Clone this repo into the current user-level Codex skills folder:

mkdir -p "$HOME/.agents/skills"
git clone https://github.com/sunflower-of-parchman/codex-hygiene.git \
  "$HOME/.agents/skills/codex-hygiene"

Then invoke $codex-hygiene. Codex normally detects newly installed skills automatically; restart Codex only if it does not appear.

Quick Measurement

From a shell:

SKILL_DIR="$HOME/.agents/skills/codex-hygiene"
"$SKILL_DIR/scripts/measure_codex_context.sh"

Use a specific window or thread id:

"$SKILL_DIR/scripts/measure_codex_context.sh" 5
"$SKILL_DIR/scripts/measure_codex_context.sh" 30
"$SKILL_DIR/scripts/measure_codex_context.sh" 5

The script prints compact counts only. It does not dump full logs, configs, tool schemas, secrets, or environment values.

Compatibility

  • Designed for macOS and Unix-like Codex Desktop environments with Bash, sqlite3, Perl, awk, and sort.
  • Uses jq and the codex CLI when available for app-cache and plugin state summaries.
  • Treats local telemetry databases and cache layouts as version-dependent diagnostic inputs, not stable APIs or billing records.
  • Supports custom Codex data locations through CODEX_HOME; use the skill's actual install path when it is not under $HOME/.agents/skills.

Safety Defaults

  • Starts read-only.
  • Uses sqlite3 -readonly.
  • Avoids printing full config, full logs, app schemas, MCP schemas, or .env values.
  • Recommends backing up ~/.codex/config.toml before any config edit.
  • Treats delete/restart/disable actions as explicit-user-approval work.

Contents

SKILL.md
agents/openai.yaml
scripts/measure_codex_context.sh
tests/measure_codex_context_test.sh
references/remediation.md
references/long-thread-replay.md

Codex References

License

MIT

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Integrations