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.
npx agentmods add skills/rijul1204/rashedul-agentic-engineering/tri-agent-loopnpx skills add Rijul1204/rashedul-agentic-engineering --skill tri-agent-loopgit clone --depth 1 https://github.com/Rijul1204/rashedul-agentic-engineeringWrote 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/rijul1204/rashedul-agentic-engineering/tri-agent-loop)<a href="https://agentmods.dev/skills/rijul1204/rashedul-agentic-engineering/tri-agent-loop"><img src="https://agentmods.dev/badge/skills/rijul1204/rashedul-agentic-engineering/tri-agent-loop.svg" alt="Measured on agentmods" 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 | $0.00193 | $0.02309 |
| Opus 5 | $0.00097 | $0.01154 |
| Sonnet 5 | $0.00039 | $0.00462 |
| Haiku 4.5 | $0.00019 | $0.00231 |
Grade A, and why
tri-agent-loop 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tri-Agent Loop
A delivery protocol that splits work across three roles and keeps each artifact rigorously vetted before it advances:
- Planner — drafts the artifact: an SRS, design doc, or per-task implementation plan. Decides what and how, not the code.
- Reviewer — adversarially reviews the artifact through a shared markdown thread, returning concrete deltas until convergence.
- Implementer — writes the actual code/change after the plan converges, and opens a PR.
The roles are pluggable: any agent can fill any role, in any order. The agent running this skill is the orchestrator — it authors artifacts when it holds a role, relays handoffs when a role belongs to an external agent, monitors the review thread, and reviews the implementer's PR. The orchestrator is usually also one of the three roles (commonly planner+reviewer), but need not be.
This is the generalized form of the workflow captured in the user's
feedback_planner_reviewer_codex_loopmemory: planner+reviewer authored by one agent, a separate implementer, every artifact Codex-reviewed before handoff. Here the agent behind each role is a parameter.
When to use
Fire when the user wants multi-agent delivery with separation of concerns:
- "Run the planner/reviewer/implementer loop on X."
- "Use Claude to plan, Codex to review, Cursor to implement" — or any role permutation.
- "Tri-agent loop", "plan-review-implement", "the docs-first Codex-reviewed loop."
- A substantial feature where the user wants each artifact adversarially reviewed before code.
Do not use for:
- Trivial / single-file changes (one agent, no ceremony).
- Pure research with no artifact to review or implement.
- When the user wants one agent to do everything end-to-end.
Step 0 — Assign the three roles
Resolve, from the user's request (ask via AskUserQuestion if unstated):
| Role | Agent | Common choices |
|---|---|---|
| planner | who drafts | this Claude · a Task subagent (Plan) · an external agent the user drives |
| reviewer | who critiques | Codex · another Claude · Gemini · a Task subagent · a human |
| implementer | who codes | Cursor · this Claude · a Task subagent · a human |
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.
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.
- 5d ago First seen · 134 lines · 193 tokens per session scan A 9ed283d82261
tri-agent-loop is a skill published in the GitHub repository Rijul1204/rashedul-agentic-engineering (2 stars, last pushed 1mo ago), licensed MIT. It adds 193 tokens to every session and 2,309 once invoked, about $0.0010 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.
Other skills, from other repositories
kanban-tui
Comprehensive kanban board and task management via ktui CLI. Use for project tracking, todo lists, task dependencies, workflow automation, and board management. Activates when user mentions boards, tasks, kanban, or project management. If the ktui command is not available, but uv is available utilize uvx kanban-tui…
life-manager
Set up and run a Trello board that actually gets things done - capture ideas, triage them into a working queue, and coach the user through what has stalled. Three modes - setup, triage, coach. Trigger on phrases like "set up my life board", "help me get stuff done", "sort my inbox", "what should I do next", "I'm…
store-sort
Sort a Trello shopping list into a supermarket's aisle-flow order, with a food-type emoji on every card. Works for any store via presets; ships a Tesco (UK) preset by default. Trigger on phrases like "sort my shopping list", "organise shopping list", "put my list in aisle order", "tesco order", "store order".
trello
Manage Trello boards, lists, and cards. Trigger on phrases like "trello", "my boards", "shopping list", "create card", "move card", "sort cards".
board-digest
Produce a plain-English status digest of a Trello board - lists and their cards, what is due or overdue, and what moved recently. Trigger on phrases like "board status", "trello standup", "what's happening on the board", "board digest", "summarise my board".
due-radar
Show what is due, overdue, or coming up across your Trello boards, sorted by date. Trigger on phrases like "what's due", "what's overdue", "trello deadlines", "due radar", "what's coming up on trello".