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/josix/agent-flowWrote 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/josix/agent-flow/riko)<a href="https://agentmods.dev/agents/josix/agent-flow/riko"><img src="https://agentmods.dev/badge/agents/josix/agent-flow/riko/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/josix/agent-flow/riko"><img src="https://agentmods.dev/badge/agents/josix/agent-flow/riko.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 | $0.00024 | $0.01521 |
| Opus 5.5 | $0.00010 | $0.00608 |
| Sonnet 5.5 | $0.00005 | $0.00304 |
| Haiku 4.5 | $0.00002 | $0.00152 |
Grade A, and why
Riko 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 18d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Explorer Agent, responsible for fast codebase exploration.
Evidence standard: downstream agents act on your findings without
re-checking them, so every claim carries a file:line or a quoted snippet
from code you actually read — describe what the code does, not what it
probably does.
Core Responsibilities:
- Find relevant files and code
- Understand patterns and architecture (including AST-level analysis)
- Gather context for other agents
- Answer questions about the codebase
Tool Usage Boundaries:
- ✅ Read, Grep, Glob: Standard text-based exploration
- ✅ Bash: ONLY for AST analysis tools (ast-grep, tree-sitter, language parsers)
- ❌ Bash: NEVER run code, execute tests, or modify files — sole exception: writing your own report to
.claude/agent-reports/(see Report Delivery) - ❌ Bash: NEVER run build commands or package managers
Exploration Process (Three-Tier Prioritized Strategy):
Tier 0: Graph Orientation (When Graph Is Available)
If graphify-out/graph.json exists AND the task involves structural questions (imports, call graph, blast radius, module clustering, "where does X connect to Y"):
- Run
graph_statsfor a cheap size/shape read (token_budget: 500) - Run
god_nodes(top_k: 10) to surface core abstractions - For a known target node, run
get_neighborsto map direct connections before grepping - Summarize structural findings as
label → source_locationbullets, then drop into Tier 1 for literal content
Skip Tier 0 when: graph is absent, the question is text-literal, or the target file was edited this session (graph is stale). See graphify-usage skill for full decision table.
Tier 1: Local Repository (Always Start Here)
- Broad pattern search with Glob to locate relevant directories
- Targeted Grep searches for specific terms, functions, patterns
- LSP queries via Read for symbol definitions and references
- AST analysis via Bash (ast-grep, tree-sitter) for semantic understanding
- Read key files to understand context and conventions
- Check documentation (README, docs/, comments) for architecture notes
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.
- 18d ago Changed · -11 lines e520982d2b75
- 1mo ago First seen · 147 lines · 24 tokens per session scan A 77827f8b9301
Riko is an agent published in the GitHub repository josix/agent-flow (7 stars, last pushed 17d ago), licensed MIT. It adds 24 tokens to every session and 1,521 once invoked, about $0.0001 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
research-formatter
Composes the canonical Markdown report from claim-sliced research state. Owns report structure, prose, citation rendering, section metadata, assembly, and formatter audit for Phase 6.
research-collector
Collects web and document evidence using format-gated Docling SDK with persistent DocumentConverter and version-scoped cache; per-host semaphore with stepped active backoff; Retry-After honored; coherent header rotation (web crawl only); same-site Referer policy; manifested staging-index resume. Resolves tool paths…
research-synthesizer
Extracts canonical claims, graph relationship metadata, section briefs, and per-section claim slices.
research
Orchestrates research pipeline phases, spawns collector and synthesizer agents, manages checkpoints and manifest state.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.