agentmods.dev

task-analyst-r1

task-analyst-r1 is an agent for Claude Code from choiyounggi/dev-loop. It costs 0 tokens per session (1,363 once invoked), scanned A, original, MIT.

A fresh-context planning agent that analyzes one development task and records the findings for a later planner. It performs only the analysis phase and writes the analysis and its approval record to specified project files.

In plain words
What is it for?
Use it to investigate a task before planning, identify relevant project information, and create the analysis artifacts that the planner will use.
Why use it?
It separates investigation from design so the plan is based on a documented understanding of the task. It also prevents the analyst from changing implementation files or starting work sessions.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dev-loop plugin — 9 skills, 11 agents, 6 hooks, 1 MCP server shipped together

not rated 6repo +1 changed 8d ago A scan 0 tokens original MIT

Good fit Use it to investigate a task before planning, identify relevant project information, and create the analysis artifacts that the planner will use.

Compare 6 agents from other repositories ↓
View source ↗ choiyounggi/dev-loop
Install

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.

Claude Code
/plugin marketplace add choiyounggi/dev-loop
Claude Code
/plugin install dev-loop

Made for: Claude Code.

Or install dev-loop, the plugin that ships this one along with the rest of its 9 skills, 11 agents, 6 hooks, 1 MCP server.

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 task-analyst-r1

README.md
[![agentmods](https://agentmods.dev/badge/agents/choiyounggi/dev-loop/task-analyst-r1/github.svg)](https://agentmods.dev/agents/choiyounggi/dev-loop/task-analyst-r1)
Your own site
<a href="https://agentmods.dev/agents/choiyounggi/dev-loop/task-analyst-r1"><img src="https://agentmods.dev/badge/agents/choiyounggi/dev-loop/task-analyst-r1/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.

agentmods 80×15 button for task-analyst-r1

Your own site · 80×15
<a href="https://agentmods.dev/agents/choiyounggi/dev-loop/task-analyst-r1"><img src="https://agentmods.dev/badge/agents/choiyounggi/dev-loop/task-analyst-r1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,363 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.01363
Opus 5.5 $0.00000 $0.00545
Sonnet 5.5 $0.00000 $0.00273
Haiku 4.5 $0.00000 $0.00136

Measured 8d ago against content hash 37267601acb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-analyst-r1 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/task-analyst-r1.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coordinator note (issue #200): this agent's frontmatter pins its model and effort (orchestrate's Tier to pipeline profile table; the -r1 copy runs the same body one effort step lower, never below high, for R1 and R0). If the Agent call dies with an HTTP 429 naming a model limit, that error is not a verdict — the caller re-runs it once with the Agent tool's model override set to whichever of opus and fable the 429 does not name, then escalates — never below Opus.

You are the per-task analyst for loop-orchestrator. You run Phase A of the bundled wiki-plan skill (Skill tool: dev-loop:wiki-plan) for exactly ONE task, in a fresh context the coordinator's own session never reaches. Phase B (Design) and Phase C (Decompose) belong to the task-planner agent, which reads your analysis.md — stop at gate-A. You are not a worker: you never call status-update.sh, you never launch a session, and you never write into a worker worktree.

Write scope

You write ONLY these paths, all inside the coordinator's checkout (your cwd):

  • {ORCH_DIR}/plans/<task>/analysis.md
  • the gate ledger .dev-loop/gates/plan-A-<task>.md You edit no tracked repo file, and you write no design.md, plan.md, tasks/, or flat plan. Before every plan-gate.sh / gate-check.sh call run export CLAUDE_PLUGIN_ROOT=<wiki root> and export GATE_CHECK_TIMEOUT=900.

Working-tree safety

NEVER git stash (any subcommand). refs/stash is repository-global — every linked worktree shares one stash stack, so a parallel worker's stash pop can retrieve YOUR uncommitted work. If you need to snapshot or restore working-tree state, use, in order: (1) git diff > <scratch>/baseline.patch

  • git apply to restore; (2) a throwaway WIP commit on the task branch (reset/amend after).

Inputs you are given (in the prompt)

  • task id
  • brief path (absolute, {ORCH_DIR}/briefs/<task>.md — the authority for scope and DoD)
  • plan dir (absolute, {ORCH_DIR}/plans/<task>/)
  • gates dir (absolute, .dev-loop/gates/)
  • risk tier (R0, R1, R2, or R3)
  • wiki root (the plugin root; CLAUDE_PLUGIN_ROOT for the gate scripts)
  • integ ref (the branch whose files are the ground truth; read them with git show <integ ref>:<path> or from the worktree the coordinator names)
  • any pointer files (issue text, user decisions, blackboard) the coordinator wants read first

Read the full file on GitHub · 104 lines

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. 8d ago Changed · +1 lines 37267601acb5
  2. 10d ago First seen · 103 lines · 0 tokens per session scan A e40105301171

Subscribe to this mod's changes

task-analyst-r1 is an agent published in the GitHub repository choiyounggi/dev-loop (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,363 tokens. 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 2026-10-06.

Claude CodePlanningbest-practicesclaude-code-plugindeveloper-toolsknowledge-basellm-agents
Related

Other agents, from other repositories

curator

Periodic consolidation pass — fold narrow agent-created skills into class-level umbrellas. Proposes intents only, never writes to disk.

tigerless-labs/autoharness · 27 tokens

qa-researcher

Scan ONE source (code, spec docs, tickets, or cc10x artifacts) and report what it says the feature does — from the user side and the system side — when a QA workflow needs a feature understanding built before test planning.

romiluz13/cc10x · 53 tokens

triage-agent

Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. No source-code writes. Routes: TRIAGE workflow.

romiluz13/cc10x · 38 tokens

architecture-scanner

Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.

romiluz13/cc10x · 47 tokens

sky-guide

Answers questions about the night sky using this astronomy atlas.

BeppeTemp/cartographer · 13 tokens

wiki-writer

Create or update wiki pages — autonomous ingest from any source, autonomous update. Auto-creates .wiki/ if missing.

Oshayr/LLM-Wiki · 28 tokens