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 skills/zeikar/hyperclaude/hyper-plan-loopnpx skills add zeikar/hyperclaude --skill hyper-plan-loopgit clone --depth 1 https://github.com/zeikar/hyperclaudeWhat 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 | $0.00071 | $0.03964 |
| Opus 5 | $0.00036 | $0.01982 |
| Sonnet 5 | $0.00014 | $0.00793 |
| Haiku 4.5 | $0.00007 | $0.00396 |
Grade A, and why
hyper-plan-loop 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 2d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hyper-plan-loop
Autonomous plan-hardening gate. Spawns the planner agent once, has it write its plan to .hyperclaude/plans/<YYYYMMDD-HHMM>-<slug>.md, runs Codex plan-review through the bridge, and revises via the still-live planner until Codex returns no blocking findings (judged by meaning, not Codex severity labels) or the cap is hit. The planner is spawned once; every revise round reuses its retained context. The reviewer is always the Codex bridge, never an agent — this preserves the "Claude builds, Codex reviews" invariant.
When to use
- User typed
/hyperclaude:hyper-plan-loop <task>. - User wants an autonomous plan → review → revise cycle in a single gesture.
Skip when:
- The task is one step — dispatch the
implementeragent directly (passrun_in_background: falsefor the result inline). - You want hands-on control over each plan / review round — use
/hyperclaude:hyper-plan+/hyperclaude:hyper-plan-reviewmanually.
Failure & recovery protocol — read first
${CLAUDE_PLUGIN_ROOT}/references/loop-protocol.md carries the shared cross-loop protocol: Spawn contract, Reply transport, Correctives and transport failures, Shared anti-patterns. references/failure-protocol.md (sibling of this file) is the plan-loop binding layer: it names this loop's reply shape (WROTE: <path>), the exact-path accept rule, the post-acceptance file/structure validation, the named reports, and what a transport failure preserves. Step 0 makes Reading BOTH mandatory before the loop starts.
Spawn & reply transport
See ${CLAUDE_PLUGIN_ROOT}/references/loop-protocol.md — Spawn contract for the Agent / SendMessage argument shapes, Reply transport for how each round's reply reaches the lead. Loop-specific bindings:
- Plan ownership: the planner writes the canonical plan file itself via caller-directed write-file mode (its Step 2 prompt carries the exact resolved path). The lead never Writes or Reads the plan body on the normal path — it does only a quiet
ok/badstructure check, and only Reads the body for human-facing failure diagnostics. Every write-file-mode reply (initial write, corrective redo, revise) is gated toWROTE: <path>-only (Step 3 accept rule).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 198 lines · 71 tokens per session scan A da9b4539a021
hyper-plan-loop is a skill published in the GitHub repository zeikar/hyperclaude (3 stars, last pushed 15d ago), licensed MIT. It adds 71 tokens to every session and 3,964 once invoked, about $0.0004 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 skills, from other repositories
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.
git-rollback
Interactively rollback Git branch to historical version; lists branches, versions, then executes reset/revert after confirmation.
golden-rss
Use when testing the rss golden build.
design-system-builder
Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…