conducty-codex

conducty-codex is a skill for Codex from robertbarclayy/conducty. It costs 77 tokens per session (741 once invoked), scanned A, original, MIT.

A set of instructions for running Conducty’s workflow inside Codex: shaping a request, planning it, tracing a small first task, executing, verifying, reviewing, and preparing to ship.

In plain words
What is it for?
Use it for coding, debugging, refactoring, reviews, CI, deployment, production changes, or other tasks that need planning and verification.
Why use it?
It adds a repeatable process for multi-step coding work, including checks, progress records, and lessons learned.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; mentions Codex.

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/robertbarclayy/conducty/conducty-codex
Any agent
npx skills add robertbarclayy/conducty --skill conducty-codex
Clone the repo
git clone --depth 1 https://github.com/robertbarclayy/conducty

Made for: Codex.

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 conducty-codex

README.md
[![agentmods](https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-codex.svg)](https://agentmods.dev/skills/robertbarclayy/conducty/conducty-codex)
Your own site
<a href="https://agentmods.dev/skills/robertbarclayy/conducty/conducty-codex"><img src="https://agentmods.dev/badge/skills/robertbarclayy/conducty/conducty-codex.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 741 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 5.1 $0.00077 $0.00741
Opus 5 $0.00039 $0.00370
Sonnet 5 $0.00015 $0.00148
Haiku 4.5 $0.00008 $0.00074

Measured 6d ago against content hash 4141ae73a014, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

conducty-codex 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 6d 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.

integrations/codex/skills/conducty-codex/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conducty Codex

Use this skill to run Conducty's loop inside Codex: Shape -> Plan -> Trace -> Execute -> Verify -> Improve -> Code Review -> Ship.

Default Moves

  1. Resolve the vault with resolve_vault; if it does not exist, call bootstrap_vault.
  2. Shape the request: goal, appetite, no-go zones, acceptance criteria, verification.
  3. Check prompt quality with check_prompt_smells before writing or dispatching prompts.
  4. Create a plan with create_plan. Every plan needs a tracer and a verification command.
  5. Execute the tracer first. If it fails, revise the plan before broader execution.
  6. Log each prompt result with log_prompt_outcome.
  7. Record group health with record_checkpoint.
  8. Record learning with record_improvement when the plan ends or a failure pattern appears.
  9. Create a pre-merge ship report with create_ship_report when verification evidence and residual risks are known.
  10. Audit the vault with audit_vault_graph when notes, links, or closure signals need a health check.

Codex Boundaries

  • Keep critical-path implementation local unless the user explicitly asks for subagents, delegation, or parallel agent work.
  • Use parallel agents only for independent work with disjoint write scopes.
  • Treat time budgets as circuit breakers: when work exceeds appetite, stop and reshape.
  • Preserve exact commands, file paths, acceptance criteria, no-go zones, and error strings.
  • Run the smallest meaningful verification before claiming completion.

Prompt Shape

Use compact prompts:

P1 - Add date helper
Context: src/date.ts, tests/date.test.ts
Accept: ISO input formats unchanged; invalid input returns null.
No-go: no timezone library swap; no API rename.
Verify: pnpm test tests/date.test.ts
Budget: 25m
Review: verify-only
Tracer: yes

MCP Tools

  • resolve_vault: show active vault path and whether it exists.
  • bootstrap_vault: create Conducty vault indexes, accumulators, and note folders.
  • get_cycle: return the operating loop and phase routing.
  • check_prompt_smells: find missing acceptance, context, verification, no-go zones, and mixed concerns.
  • create_plan: write a timestamped plan note and update Plans Index.
  • list_recent_notes: list recent plans, improvements, code reviews, ship reports, or accumulator notes.
  • log_prompt_outcome: prepend a terse entry to Prompt Log.
  • record_checkpoint: append group health metrics to the plan note.
  • record_improvement: write an improvement kata note and update Improvements Index.
  • create_ship_report: write a green/yellow/red pre-merge verdict with verification evidence and residual risks.
  • audit_vault_graph: report broken wikilinks, duplicate basenames, orphan user notes, plans without ship reports, and plans without checkpoints.

Read the full file on GitHub · 68 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. 6d ago First seen · 68 lines · 77 tokens per session scan A 4141ae73a014

Subscribe to this mod's changes

conducty-codex is a skill published in the GitHub repository robertbarclayy/conducty (176 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 741 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 2026-08-30.