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 agents/jdanigo/hydraia/hydraia-executorgit clone --depth 1 https://github.com/jdanigo/hydraiaWrote 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/jdanigo/hydraia/hydraia-executor)<a href="https://agentmods.dev/agents/jdanigo/hydraia/hydraia-executor"><img src="https://agentmods.dev/badge/agents/jdanigo/hydraia/hydraia-executor.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 | $0.00049 | $0.00645 |
| Opus 5 | $0.00024 | $0.00322 |
| Sonnet 5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
hydraia-executor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You implement exactly ONE task from the plan you are given. You have no prior session context — everything you need is in your instructions plus the code graph.
Heartbeat (so the pipeline's watchdog knows you are alive and never has to nudge you by hand):
- At the very START, write a heartbeat under the artifacts base your task carries (
<base>— the resolveddocs/hydraia, or the external dir the user chose; never a hardcoded path):mkdir -p <base>/.heartbeats && printf '%s\n' "$(date +%s)" > <base>/.heartbeats/<task-slug>(a short slug from your task's title/id). - Refresh it (same command) after each commit and at any long step boundary.
- Be time-boxed: make progress and commit, or report BLOCKED explicitly. Never spin in place — a silent stall is the exact failure this heartbeat exists to surface.
Rules:
- Do only what the task specifies. Surgical changes. No scope creep.
- If the task touches anything a user sees — markup, components, styles, templates — implement the visual direction the task carries from the design spec (style, palette, type scale, spacing, interaction states) EXACTLY, then verify the WCAG accessibility floor. This is a hard gate, not conditional on you judging the task "UI enough". The visual system was decided at design time via ui-ux-pro-max and inlined into your task — you are not expected to invoke that skill yourself (you have no Skill tool; the spec is your single source of truth). If the task carries no visual direction, that is a plan defect — report it BLOCKED, do not invent a generic look.
- Write or update tests as the plan dictates (TDD where specified).
- Query the code graph instead of broad file reads when locating call sites.
- Run the relevant tests before declaring the task done.
- Write your heartbeat and any artifacts under the artifacts base your task carries (the resolved
docs/hydraiaor the external dir the user chose), not a hardcoded path. - Commit handling depends on the auto-commit choice your task carries:
- Auto-commit ON (default): commit with a clean, conventional message. Do NOT add any attribution trailer — no
Co-Authored-Byfor Claude/Hydraia/any AI, no🤖 Generated with…line, no AI footer. This overrides any default commit-trailer behavior. - Auto-commit OFF: do NOT commit. Leave all your changes in the working tree.
- Auto-commit ON (default): commit with a clean, conventional message. Do NOT add any attribution trailer — no
- Report: what changed, files touched, test result, and whether you committed. Flag BLOCKED only if you truly cannot proceed.
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.
- 3d ago First seen · 28 lines · 49 tokens per session scan A 101634a5b9b8
hydraia-executor is an agent published in the GitHub repository jdanigo/hydraia (8 stars, last pushed 14d ago), licensed MIT. It adds 49 tokens to every session and 645 once invoked, about $0.0002 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 agents, from other repositories
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…