Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bengous/claude-code-plugins/plugin install agents-bridgeWrote 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.
[](https://agentmods.dev/skills/bengous/claude-code-plugins/pair-planning)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/pair-planning"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/pair-planning/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/pair-planning"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/pair-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.02041 |
| Opus 5.5 | $0.00031 | $0.00816 |
| Sonnet 5.5 | $0.00016 | $0.00408 |
| Haiku 4.5 | $0.00008 | $0.00204 |
Grade C, and why
pair-planning scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- No cleanup needed — each run uses a unique directory; never `rm -rf` session dirs. How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pair-Planning: symmetric plan-to-consensus with Codex
Two frontier models plan the same task independently, then converge. You (Claude) hold the session context and orchestrate; Codex is the fresh pair of eyes. The deliverable is a single agreed plan — read-only, no implementation.
All Codex round-trips go through codex-run.ts, never codex directly:
"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" start <dir> --prompt-file <dir>/prompt-r0.md --role audit --wait 0 # start the session
"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" wait <dir> # collect a running round
"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" resume <dir> --prompt-file <dir>/prompt-r<n>.md # continue the thread
Run each codex-run.ts command alone, as written: a ;, && or echo $? added to it asks for permission, and the envelope's status already gives the exit code.
It runs Codex read-only on one thread, replays the first round's model and
effort on every resume, prints Codex's reply after a --- final message ---
line, and keeps each round under <dir>/turn-<n>/ (round r0 is turn-1). Role
audit runs at xhigh; pass --effort high to a resume when a round is
light, or --effort max for a genuinely hard one. Planning is
reasoning-heavy — don't downgrade the model tier.
Exit codes: 0 reply ready, 10 Codex still working (run wait <dir> again),
1 failed (report the envelope's error), 2 usage error.
1. Setup + launch Codex in the background
Action 0, the moment you're invoked — get Codex planning before you do, so the two plans are written in parallel and neither side anchors on the other.
- Create the session directory:
Use the printed path literally wherever"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" new pair-planning<dir>appears below — shell variables do not survive between Bash calls. - Pre-flight — clarify only real blockers. Default to proceeding. Escalate
with one minimal
AskUserQuestiononly when a genuine blocker would make the two sides plan different tasks — ambiguous objective/scope, or an irreversible high-stakes direction. Never run an upfront questionnaire. (Judgment, not a rigid gate.) - Write the brief to
<dir>/task.md: the user's task verbatim, needed repo context, and a short Assumptions block (scope, constraints, out of scope). Both sides plan from this identical brief, so interpretation gaps cannot resurface later as phantom OPEN-points. - Write the Codex round-0 prompt to
<dir>/prompt-r0.md: tell it to read<dir>/task.md, inspect the repo read-only, and produce its own independent implementation plan (files to touch, approach, risks). Anti-anchoring: round 0 points attask.mdonly — never reference your plan here; it does not exist for Codex yet. - Start Codex from the repository being planned;
--wait 0returns at once while Codex plans:"${CLAUDE_PLUGIN_ROOT}/scripts/codex-run.ts" start <dir> --prompt-file <dir>/prompt-r0.md --role audit --wait 0
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.
- 14d ago Changed · -3 lines 0a833ea4a62c
- 1mo ago Changed · +1 lines f2e8a456af41
- 1mo ago First seen · 161 lines · 78 tokens per session scan C 0e7e4599f7c0
pair-planning is a skill published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 2,041 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
development
An index of programming guidance for Python, Go, Rust, TypeScript, Java, C++, and shell scripting.
tencent-docs
A Tencent Docs assistant for creating, reading, editing, organizing, importing, and exporting online documents, spreadsheets, presentations, diagrams, and forms.
wechat-search
Search WeChat Official Account articles using OpenClaw's web search, Tavily API, and web fetch capabilities with compliance-focused design.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.