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 commands/harshvardhan86/claude-wave-plugin/wave-checkpointgit clone --depth 1 https://github.com/Harshvardhan86/claude-wave-pluginWrote 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/commands/harshvardhan86/claude-wave-plugin/wave-checkpoint)<a href="https://agentmods.dev/commands/harshvardhan86/claude-wave-plugin/wave-checkpoint"><img src="https://agentmods.dev/badge/commands/harshvardhan86/claude-wave-plugin/wave-checkpoint.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 5.1 | $0.00033 | $0.00343 |
| Opus 5 | $0.00016 | $0.00171 |
| Sonnet 5 | $0.00007 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
wave-checkpoint 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 6d 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
Wave checkpoint
Context
- Working dir: !
pwd - Timestamp: !
date -u +%Y-%m-%dT%H:%M:%SZ - Git head: !
git rev-parse --short HEAD 2>/dev/null || echo "no-git" - Status: !
git status --porcelain 2>/dev/null | wc -l | tr -d ' 'changed files
Instructions
Save a wave checkpoint to .wave/checkpoints/<timestamp>.md containing:
- Wave goal — the original feature description from
/wave-start. - Phase reached — which of AC / DR / RED / GREEN / TEET is currently in flight.
- Last verified evidence — paste the most recent screenshot path, test output, or computed-style assertion result. NOT "tsc passes". Real evidence only.
- Open questions — anything the user still has to decide.
- Resume instructions — exact commands and prompts a fresh session would need to pick up where this one left off.
If .wave/ does not exist, create it. Add .wave/ to .gitignore if a git repo and the entry is missing.
After writing the checkpoint, print the file path and the resume command to the user. Do not commit checkpoints — they're local recovery state, not source.
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.
- 6d ago First seen · 28 lines · 33 tokens per session scan A 0e7e646a7933
wave-checkpoint is a command published in the GitHub repository Harshvardhan86/claude-wave-plugin (8 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 343 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 commands, from other repositories
resume
Resume an interrupted workflow from where it left off.
fierce-option-panel
Default-on interview option-quality panel (Workflow tier) — diverse generators, majority-vote consensus, cautious-confidence judge, top-K.
fierce-review
Deterministic adversarial code review (Workflow tier) for high-stakes scope.
fierce-compete
Deterministic competitive code tournament (Workflow tier) — best of N implementations.
fierce-debate
Deterministic adversarial debate (Workflow tier) for high-stakes decisions.
design-review
Compare design (Figma URL or mockup image) against implementation to detect UI mismatches (colors, layout, typography).