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/harness-mini/harness-mini/stage-viewernpx skills add harness-mini/harness-mini --skill stage-viewergit clone --depth 1 https://github.com/harness-mini/harness-miniWrote 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/skills/harness-mini/harness-mini/stage-viewer)<a href="https://agentmods.dev/skills/harness-mini/harness-mini/stage-viewer"><img src="https://agentmods.dev/badge/skills/harness-mini/harness-mini/stage-viewer.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 | $0.00069 | $0.01203 |
| Opus 5 | $0.00034 | $0.00602 |
| Sonnet 5 | $0.00014 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
stage-viewer 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 5d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the main agent holding the tiller. Only you advance the FSM.
On entry — check for a newer harness (first thing)
Before routing work in a fresh session, run bin/harness.sh version (or read the
update: line status prints). If a newer harness-mini is published, tell the
user and offer bin/harness.sh update before proceeding — the update is
checksum-guarded (your edits are kept). It's best-effort: skip silently if
offline. Then continue.
View
- List
docs/exec-plans/active/*.md. For each, read thestage:frontmatter. - Report a one-line status per plan:
<plan> — <stage> — <one-line "Now">. - Read
.trace/checkpoints/for the latest checkpoint of a plan if you need to resume it.
Route (simple vs complex)
- Simple (one obvious change, <1 slice): quick mode — skip planning
ceremony, go straight to
implementwith a lightweight plan note (docs/templates/quick-plan.md); evaluate at L0/L1. - Complex (multi-step, ambiguous, cross-cutting): full mode — run the full
funnel (intake→prd→issues) before implementing
(
docs/templates/full-plan.md); evaluate at L1/L2.
Record the chosen evaluation tier in the plan's eval: field (see the evaluate
skill); the evaluate exit condition below reads it.
Plan-stage write ban (convention — no permission engine)
While an active plan's stage is intake, prd, or issues,
agents MUST NOT modify product code. Allowed edits in those stages:
docs/(includingdocs/exec-plans/).trace/(checkpoints, evals, garden backlog)- harness plan/skill/agent docs only when the change is the plan itself (e.g. writing this plan's PRD) — not drive-by refactors of unrelated skills
Product code (application source, and for harness-mini itself: bin/ behavior
changes unrelated to the plan's stated issues) waits until stage: implement.
This is a convention enforced by the main agent / planner — Mini does not
ship a git dirty-tree checker. Cold sessions: prefer bin/harness.sh status
(ready: line) before acting.
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.
- 5d ago First seen · 86 lines · 69 tokens per session scan A df381665308f
stage-viewer is a skill published in the GitHub repository harness-mini/harness-mini (2 stars, last pushed 25d ago), licensed MIT. It adds 69 tokens to every session and 1,203 once invoked, about $0.0003 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 skills, from other repositories
foblex-flow
Authoritative guide for working with Foblex Flow (@foblex/flow) in the skill-map UI. Use whenever editing Angular code in ui/ that touches graph rendering — templates with f-flow / f-canvas / f-connection / fNode / fConnector / fDraggable / fZoom / fMarker directives; TypeScript importing from @foblex/flow…
content-editor
Writes and edits the portfolio's pages. Reads a brief, follows the style guide, and emits the HTML into public/.
notion-publish
Mirrors the portfolio's pages into Notion after publishing, creating one Notion page per site page via the Notion MCP. Use it from /publish, or when the user asks to sync the site to Notion.
publish
Publishes the portfolio: runs the link check, hands off to the content editor for any last fixes, then follows the deploy runbook.
check-links
Validates the portfolio's internal links before publishing. Walks every generated page and reports any link whose target is missing.
master-skill
Example skill paired with the master-agent for the advanced tutorial. Links to the agent so extractors and analyzers have something to chew on.