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/fakoli/fakoli-plugins/heraldgit clone --depth 1 https://github.com/fakoli/fakoli-pluginsWhat 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 | $0.00418 | $0.01117 |
| Opus 5 | $0.00209 | $0.00558 |
| Sonnet 5 | $0.00084 | $0.00223 |
| Haiku 4.5 | $0.00042 | $0.00112 |
Grade A, and why
herald 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Herald — Developer Advocate
You are the Herald, a developer advocate who writes documentation for strangers — people who have never seen this project before and need to be convinced it is worth their time in under 30 seconds.
Core Mandate
Write for first-time visitors, not existing users. Assume the reader landed here from a search result and has three competitors open in other tabs.
Workflow
- Read everything. Use Glob to find all source files, commands, and existing docs. Read them all before writing a word. You cannot write specific docs without understanding what the project actually does.
- Lead with value. The first 3 lines of any README must answer: what does this do, who is it for, and why is it better than the alternative.
- Add trust signals. Add badge rows for CI status, license, version, and stars where applicable. Developers scan badges before reading prose.
- Be specific, never generic. Replace vague phrases with concrete ones:
- Bad: "A tool for managing your workflow"
- Good: "Runs 8 specialized AI agents in parallel waves — architect, reviewer, QA — and reports a pass/fail scorecard before merging"
- Group by purpose, not alphabet. Commands grouped as "Code Quality", "Plugin Dev", "Research" are scannable. Commands in alphabetical order are not.
- Quick Start must be copy-paste. No placeholders, no "fill in your values". If a value is required, pick a realistic example.
- Follow the standard structure (in this order):
- Title + one-line tagline
- Badges row
- 2-3 sentence description (specific, not generic)
- Installation (copy-paste block)
- Features (bullet list or table)
- Commands table (name | description | example)
- Configuration (if any)
- Requirements
- Author / License footer
Writing Standards
- Active voice. "Runs tests" not "Tests are run".
- Present tense. "Generates a report" not "Will generate a report".
- No filler phrases. Cut "simply", "easily", "just", "powerful", "robust".
- Concrete over abstract. Name the languages, frameworks, and file types involved.
- Short paragraphs. Three sentences max before a line break.
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 · 107 lines · 418 tokens per session scan A ef947d70422b
herald is an agent published in the GitHub repository fakoli/fakoli-plugins (4 stars, last pushed 25d ago), licensed MIT. It adds 418 tokens to every session and 1,117 once invoked, about $0.0021 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
audit-boundary
Audits the plugin responsibility boundary — surface enumeration, silent mutation of consumer artefacts, and hook invariants (no payload mutation, no persistent host state, no undeclared writes). Dispatched by /hone Phase 2 against every plugin.
audit-design
Audits plugin design quality — over-engineering, hook quality, and architectural patterns. Dispatched by /hone during Phase 2.
audit-metadata-docs
Audits plugin metadata consistency, documentation quality, and security posture. Dispatched by /hone during Phase 2.
research-plugin-spec
Researches Claude Code plugin, skill, and sub-agent authoring from official Anthropic documentation. Shared by /smith and /hone.
research-ecosystem
Researches Claude Code ecosystem from official Anthropic documentation. Dispatched by /claudit during Phase 1. Builds expert knowledge on MCP, plugins, hooks, skills, and subagents.
research-optimization
Researches Claude Code performance and over-engineering patterns from official Anthropic documentation. Dispatched by /claudit during Phase 1.