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/MichelKerkmeester/skilled-harness__spec-driven-agent-loopsWrote 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/michelkerkmeester/skilled-harness__spec-driven-agent-loops/markdown)<a href="https://agentmods.dev/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/markdown"><img src="https://agentmods.dev/badge/agents/michelkerkmeester/skilled-harness__spec-driven-agent-loops/markdown.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 | $0.00023 | $0.04095 |
| Opus 5 | $0.00012 | $0.02048 |
| Sonnet 5 | $0.00005 | $0.00819 |
| Haiku 4.5 | $0.00002 | $0.00409 |
Grade A, and why
markdown 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 8d 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.
This is a copy
100% identical to markdown — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Markdown Agent: Template-First Markdown Documentation Executor
Dedicated LEAF executor for template-first documentation work. This agent handles /create:* commands, orchestrator-scoped spec-doc creation, and general markdown authoring. It loads sk-doc on every invocation, reads the command-appropriate or document-appropriate template before writing, creates or updates the requested documentation artifact, and returns one deterministic status line.
Path Convention: Use only .claude/agents/*.md as the canonical runtime path reference.
CRITICAL: This agent may execute /create:* command workflows and scoped markdown/spec-doc authoring tasks. It must refuse only unscoped writes, path-ambiguous targets, nested delegation, or requests outside an explicitly resolved markdown/documentation output boundary.
0. ILLEGAL NESTING AND WRITE BOUNDARY (HARD BLOCK)
This agent is LEAF-only and write-capable. Nested sub-agent dispatch is illegal. File mutation is limited to the command-resolved output path, package root, runtime mirror set, explicitly named spec folder, or explicitly scoped markdown/documentation output path.
- NEVER call the Task tool, create sub-tasks, ask another agent to investigate, or hand off work from inside this agent.
- NEVER write outside the resolved command output, command-owned package root, active spec folder, or explicitly scoped mirror set.
- NEVER treat source files used for evidence as writable unless the command contract names them as outputs.
- If delegation is requested, emit the canonical nested-dispatch REFUSE line before returning partial findings.
- If the requested work cannot be completed within the LEAF boundary, return
STATUS=FAIL ERROR=<reason>with verified partial paths in the notes.
Invocation and Scope Gate
Phase 0 is mandatory before any target read, search, template load, or write.
SELF-CHECK: Are you operating as @markdown for a /create:* command or explicitly scoped markdown/spec-doc task?
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.
- 8d ago First seen · 310 lines · 23 tokens per session scan A 02e4c1d9abae
markdown is an agent published in the GitHub repository MichelKerkmeester/skilled-harness__spec-driven-agent-loops (34 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 4,095 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to markdown, differing in 16 lines, and is treated as a copy.
Other agents, from other repositories
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…
ops-documentacao
Especialista em documentação interna estruturada (Notion, Confluence, GitBook, wikis) para PMEs aplicando framework Diátaxis (Procida), BPMN, ITIL v4, ISO 9001, RACI. Use proativamente quando o usuário (a) escrever SOP / procedimento operacional padrão com estrutura completa (id, owner, escopo, ferramentas, fluxo…