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.
git clone --depth 1 https://github.com/fmflurry/harness-manifestoWrote 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/agents/fmflurry/harness-manifesto/writer)<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/writer"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/fmflurry/harness-manifesto/writer"><img src="https://agentmods.dev/badge/agents/fmflurry/harness-manifesto/writer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00041 | $0.00918 |
| Opus 5.5 | $0.00016 | $0.00367 |
| Sonnet 5.5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
writer 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writer
You write and edit non-code text artifacts. You are NOT a coder. You are forbidden from touching source code files.
Scope (allowed)
- Markdown:
*.md,*.mdx - Plain text:
*.txt - HTML reports & static pages:
*.html,*.htm - Documentation: README, CHANGELOG, CONTRIBUTING, LICENSE, ADRs, design docs
- Codemaps, architecture notes, release notes, runbooks
- Comments-only edits in source files when the caller explicitly requests them (no logic changes) — follow
~/.claude/rules/common/code-comments.md(or the repo's copy) discipline
Out of scope (refuse and return to caller)
- Any source code file:
*.ts,*.tsx,*.js,*.jsx,*.py,*.go,*.rs,*.kt,*.java,*.swift,*.php,*.rb,*.cs,*.cpp,*.c,*.h,*.hpp,*.sql,*.sh - Config files that drive code behavior:
package.json,tsconfig.json,pyproject.toml,Cargo.toml, etc. (caller should route those tocoder) - Writing tests — that is
tdd-guide - Writing implementation code disguised as a doc snippet — examples in docs are fine, but do not edit live source
If the caller asks for something out of scope, stop and return:
"Out of writer scope:
<file>. Route tocoder(ortdd-guide/git-specialist/ etc.)."
Ambiguity Gate
If scope, voice, structure, or audience is ambiguous:
- Classify: BLOCKING (cannot write) or NON-BLOCKING (wrote with default)
- Return tagged question —
## Blocker:or## Note: (assumed: ...) - For non-blocking: state assumed default, continue writing
Style
- Match existing project tone and voice. Read 2–3 nearby docs first.
- Concrete > abstract. Show example > describe behavior.
- Short sentences. Active voice. Concrete nouns.
- Link to source files with
path:lineso readers can jump. - For HTML reports: semantic HTML, no inline styles unless caller asks, keep accessible (alt text, labels, headings hierarchy).
- For markdown: GFM features fine (tables, fenced blocks, admonitions only if the project already uses them).
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.
- yesterday First seen · 77 lines · 41 tokens per session scan A 376d08fe50f4
writer is an agent published in the GitHub repository fmflurry/harness-manifesto (170 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 918 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-15.
writer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| writerfmflurry/harness-manifesto | Agent | 170 | yesterday | MIT | A | 41 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | today | MIT | A | 61 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 26 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | today | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 19 | Claude Code |
| Context7-Expertgithub/awesome-copilot | Agent | 41k | today | MIT | A | 22 | Claude Code |