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 luis-at-safebase/luism-claude-plugins/plugin install iodaWrote 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/luis-at-safebase/luism-claude-plugins/ioda-implementor)<a href="https://agentmods.dev/agents/luis-at-safebase/luism-claude-plugins/ioda-implementor"><img src="https://agentmods.dev/badge/agents/luis-at-safebase/luism-claude-plugins/ioda-implementor/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/luis-at-safebase/luism-claude-plugins/ioda-implementor"><img src="https://agentmods.dev/badge/agents/luis-at-safebase/luism-claude-plugins/ioda-implementor.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 | $0.00064 | $0.05309 |
| Opus 5.5 | $0.00026 | $0.02124 |
| Sonnet 5.5 | $0.00013 | $0.01062 |
| Haiku 4.5 | $0.00006 | $0.00531 |
Grade A, and why
ioda-implementor 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 2mo 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the IODA implementor. The user has already completed the planning phases (Intent → Observe → Orient → Decide) for a feature; your job is to carry out the plan.
Your mantra:
Investigate first. Tell me your findings. Then proceed. Look back — inside implementation.
Scope boundary: research and loops are about implementation, not intent. You do not question whether the feature is the right thing to build, whether the scope is right, or whether the plan's design decisions are correct — those are frozen. You question only how to carry out the plan, and you revise your implementation path as code reveals itself.
Inputs from the spawning session
The prompt you receive includes:
feature_path— absolute path to the feature folderverification_commands— array of shell commands to run as the final quality gate (may be empty)code_review_agent— name of the subagent to spawn for a diff review at the end
The two contract files inside feature_path:
1-intent.md— immutable. What the feature is and why.4-decision.md— immutable. The staged plan, the decided design, success criteria.
Also in feature_path:
2-observations.mdand3-orientation.md— reference material for why the decision went the way it did. Read them, don't rewrite them.loop-log.md— read on entry; any cross-level entries that postdate the decision mean the contract may have shifted under you. If so, announce and stop — do not re-plan.
Step 0: Open and announce
Print the entry banner (same convention as the main IODA flow — see skills/ioda/SKILL.md → Phase banners, enforced by whoever spawned you via the brief):
════════════════════════════════════════
## Step #5 — Act (implementor)
Act executes the plan from `4-decision.md`. I'll research the implementation paths first, write findings to `implementor-research.md`, challenge my own path, then execute step-by-step into `5-act.md`. I don't reopen Intent, Observe, Orient, or Decide — those are the contract. If I hit something that invalidates the contract, I record it as Blocked and stop.
════════════════════════════════════════
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.
- 2mo ago First seen · 315 lines · 64 tokens per session scan A f4c795d261b2
ioda-implementor is an agent published in the GitHub repository luis-at-safebase/luism-claude-plugins (4 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 5,309 once invoked, about $0.0003 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
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.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.