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/a554b554/reactant/resolvenpx skills add a554b554/Reactant --skill resolvegit clone --depth 1 https://github.com/a554b554/ReactantWhat 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 | $0.00017 | $0.00527 |
| Opus 5 | $0.00009 | $0.00264 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
resolve 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve
Finalize a revision by applying the plan from preceding tags to the original content.
Input
- File path: the file being processed.
- Surrounding text: the text before the tag chain, plus the full chain of tags (e.g.,
<@plan: ...><@output: ...><@resolve>or a multi-turn chain like<@plan: ...><@output: ...><@plan: ...><@output: ...><@resolve>). - Prompt: typically empty for resolve.
The tag chain may contain a single <@plan>/<@output> pair, or a multi-turn conversation consisting of multiple <@plan>/<@output> pairs. Each pair represents one turn of iterative refinement.
Workflow
- Read the original content (the text before the tag chain).
- Read the full conversation history — all
<@plan>/<@output>pairs in sequence. The final<@output>represents the most refined plan, but earlier turns provide context for intent and constraints. - Apply the plan to the original content. When multiple turns exist, the last
<@output>takes precedence, but use earlier turns to resolve ambiguity about what the user intended. - Write the result back to the file: replace the entire block (original content + all tags) with the revised text.
Scope Modifiers
The original content may contain scope modifier tags that constrain which regions the plan can be applied to.
- Protect
<< >>: Text inside<<and>>must NOT be modified, even if the plan suggests changes to it. Remove the<<>>delimiters in the output, but keep the content unchanged. - Field
(( )): ONLY the text inside((and))may be modified by the plan. The surrounding text is context only — do not change it. Remove the(())delimiters in the output.
If neither modifier is present, the entire original content is editable (default behavior).
Rules
- Follow the plan faithfully.
- Respect scope modifiers: never edit protected regions, only edit field regions when present.
- All tags (
<@plan: ...>,<@output: ...>,<@resolve>) and all scope modifier delimiters (<< >>,(( ))) must be removed; only clean text remains.
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 · 39 lines · 17 tokens per session scan A 25ec31fc04f7
resolve is a skill published in the GitHub repository a554b554/Reactant (54 stars, last pushed 29d ago), licensed MIT. It adds 17 tokens to every session and 527 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…