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/executenpx skills add a554b554/Reactant --skill executegit 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 | $0.00025 | $0.00757 |
| Opus 5 | $0.00013 | $0.00378 |
| Sonnet 5 | $0.00005 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
execute 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute
Route all <@skill-name: ...> annotations in a file to their matching skill subagents.
Usage
/execute <filename>
Grammar
<@skill-name: prompt>
Tags are written inline, directly in the original text. <@output: ...> is a special data tag — never dispatched, only consumed by other skills.
Modifiers
Prompts may contain context references ( path ) that point the skill agent to external resources (files, sections, etc.). The execute router does not interpret these — they are passed through to the subagent as part of the prompt.
Skill registry
| Tag | Skill | Description |
|---|---|---|
<@edit: ...> |
edit |
Generic edit per prompt. |
<@proofread> |
proofread |
Fix grammar, spelling, punctuation. |
<@plan: ...> |
plan |
Produce a revision plan. |
<@ph> / <@ph: ...> |
ph |
Fill placeholder from context. |
<@resolve> |
resolve |
Apply preceding plan/output chain. |
<@figure: ...> |
figure |
Generate a figure. (Placeholder — needs Gemini API.) |
<@cite: ...> |
cite |
Find and insert citations to support a claim. |
<@plot: ...> |
plot |
Generate and execute a data visualization script. |
To add a new skill: create skills/<name>/SKILL.md and add a row to this table.
Subagent contract
Every subagent receives:
- File path — the full path of the file being processed.
- Surrounding text — the paragraph or block where the tag appears (including any chained tags like
<@output: ...>). - Prompt — the text inside the tag after the skill name.
Each subagent is responsible for applying its own changes directly to the file. The execute skill does not write back results — it only dispatches.
Workflow
- Clear context — disregard all prior conversation context. Start fresh with only this skill's instructions.
- Read the target file.
- Scan for all
<@...>tags, top to bottom. - For each tag:
- Skip
<@output: ...>— it is data, not a dispatch target. - Look up the skill name in the registry above.
- If unknown, skip and warn the user.
- Spawn a subagent with the matching skill. Pass the file path, surrounding text, and prompt.
- The subagent applies changes directly to the file.
- Re-read the file before processing the next tag (the file may have changed).
- Skip
- Report a brief summary of how many tags were processed.
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 · 75 lines · 0 tokens per session scan A 3af4b166deb9
execute is a skill published in the GitHub repository a554b554/Reactant (54 stars, last pushed 29d ago), licensed MIT. It adds 25 tokens to every session and 757 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
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
agentmail
Use when an agent needs AgentMail CLI email inboxes.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.