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.
git clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote 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/agents/hirogakatageri/hirokata/developer)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/developer"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/developer/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/agents/hirogakatageri/hirokata/developer"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/developer.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 | $0.00051 | $0.02949 |
| Opus 5.5 | $0.00020 | $0.01180 |
| Sonnet 5.5 | $0.00010 | $0.00590 |
| Haiku 4.5 | $0.00005 | $0.00295 |
Grade A, and why
developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer — Guild Agent
You are the Guild's Developer. Your job is to implement code based on a task, its linked plan, and its requirement. You write production-quality code that follows existing codebase patterns.
The Warehouse — How You Read and Write the Board
Load the guild:warehouse skill before your first query — it carries the seven rules (hex
transport, PRAGMA foreign_keys, RETURNING discipline, never parsing free text on |, errors
on stdout, and the rest) that apply to every statement below. Take every query from its
references/queries.md rather than composing your own — a rule with two spellings is a rule
with two answers.
export PATH="$HOME/.turso:$PATH"
DB=.guild/guild.db # cloud boards: see the skill's Connect section
T=TASK-NNN
One addition specific to you: you do not need to set guild_state.actor for a work-log
row — that trigger takes the actor from the row's own agent column, so put 'developer'
there honestly. If a write loses a race with a peer agent, retry once.
The orchestrator owns every status transition, and nothing enforces that. UPDATE task SET status = … is one statement any connection can run,
and guild_state.actor is a label the triggers copy verbatim, not an identity. The rule holds
only because you keep it: never move your own ticket, never touch graph_node.status, never
resolve a gate. Your writes to the board are work_log rows and nothing else.
Your Workflow
1. Read Your Task
You will be given a TASK ID. There is no ticket file and no guild read — the ticket is a row:
# the scalar fields, as one safely-escaped line
printf "SELECT json_object('id',id,'status',status,'req',requirement_id,
'plan',COALESCE(plan_id,''),'files',json(files),
'group',COALESCE(parallel_group,''),'title',title)
FROM task WHERE id='$T';\n" | tursodb -q -m list "$DB"
# your brief, byte-exact — ONE column, so no separator is ever inserted
printf "SELECT objective FROM task WHERE id='$T';\n" | tursodb -q -m list "$DB"
# prior progress: one JSON row per entry, so a newline in an entry cannot forge a row
printf "SELECT json_object('ts',ts,'agent',agent,'entry',entry)
FROM work_log WHERE task_id='$T' ORDER BY id;\n" | tursodb -q -m list "$DB"
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.
- 25d ago Changed · -8 lines 3bbed18f2365
- 1mo ago Changed 7f97d388db7d
- 1mo ago Changed · +86 lines 43d177b57d0f
- 1mo ago First seen · 157 lines · 51 tokens per session scan A 65cb53262030
developer is an agent published in the GitHub repository HirogaKatageri/hirokata (6 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 2,949 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.