Skip to content
Agentmart
Submit a tool

fulcra-harness-dashboard

Adapts fulcra-project-dashboard into a safe, manager-facing view for a task-specific agent control harness: milestone/PR timeline, run evidence, durable…

Skill by fulcradynamics

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying fulcra-harness-dashboard?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/fulcradynamics-fulcra-harness-dashboard

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Adapts fulcra-project-dashboard into a safe, manager-facing view for a task-specific agent control harness: milestone/PR timeline, run evidence, durable status summary, decision requests, escalations, and optional curated publication.

Use cases: data, productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/fulcra-harness-dashboard

What's inside

Skill name
fulcra-harness-dashboard
Description
Adapts fulcra-project-dashboard into a safe, manager-facing view for a task-specific agent control harness: milestone/PR timeline, run evidence, durable status summary, decision requests, escalations, and optional curated publication.
License
MIT
Instructions
198 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • files: referenced but missing: templates/dashboard-data.json, templates/harness-dashboard-components.js, templates/harness-dashboard-components.css, templates/harness-dashboard-theme.css, templates/public/noindex-head.html

Files (9)

  • SKILL.md
  • refresh_harness_dashboard.cpython-311.pyc · scripts/__pycache__/
  • refresh_harness_dashboard.py · scripts/
  • dashboard-data.json.template · templates/
  • harness-dashboard-components.css.template · templates/
  • harness-dashboard-components.js.template · templates/
  • harness-dashboard-theme.css.template · templates/
  • noindex-head.html.template · templates/public/
  • publish_surge.sh.template · templates/

SKILL.md (first lines)

# Fulcra Harness Dashboard

This is an **adaptation of `fulcra-project-dashboard`**, not a replacement
for it. Start by following that skill's static-triad/dashboard setup. Then
apply only the control-harness-specific additions below.

## Purpose

A project dashboard answers “what has the team done?” A harness dashboard
also answers:

- Which milestone is current, passed, blocked, or queued?
- What did the most recent Generator/Evaluator run prove?
- Is the current issue a user decision, a genuine escalation, or transient
  provider capacity?
- What is the concise “where we are / where we're going / next bearing”
  state?
- Did the milestone PR merge, remain reviewable, or fail evaluation?

## Required durable Workspace inputs

Read only the control harness's durable artifacts:

```text
team/<team>/status-summary.md
team/<team>/milestone-progress.md
team/<team>/progress.md
team/<team>/decision/
team/<team>/escalation/
team/<team>/artifact/*verdict*.md
team/<team>/member/*/progress.md
```

Do not infer status from Discord history, transient local model output, or
scheduler “completed” status alone.

## Base setup

1. Invoke `fulcra-project-dashboard` to build the base static triad and its
   manager-oriented layout.
2. Copy `templates/dashboard-data.json` as the curated data contract and
   use `scripts/refresh_harness_dashboard.py` to refresh it from downloaded
   `status-summary.md` and `milestone-progress.md`.
3. Copy `templates/harness-dashboard-components.js` and
   `templates/harness-dashboard-components.css` into the base dashboard's
   public static-triad assets. Add a root element such as
   `<section id="harness-dashboard"></section>` and call
   `renderHarnessDashboard(root, data)` after the base dashboard loads the
   curated JSON. The component supplies actual rendering for the flight
   plan, checkpoint, interactive run timeline, previous-run context, and
   Open Items; it deliberately does not replace the base dashboard shell.
4. Keep the base dashboard's executive summary, logs, progress, timeline,
   and activity visuals where useful; these adaptations make those views
   control-loop aware.

## Required project theming (restrained)

Before the first dashboard publication, establish a small project-specific
visual theme. A harness dashboard must not look like an unmodified generic
admin page, but theme must improve orientation rather than compete with
operational data.

Required minimum:

1. a project-specific dashboard title/subtitle and section copy;
2. a restrained palette (accent, soft accent, ink, paper/background) tied
   to the project domain;
3. one small motif or visual cue (symbol, border treatment, or compact
   header mark) relevant to the project;
4. readable contrast and unchanged access to milestones, runs, decisions,
   and escalations.

Start with `templates/harness-dashboard-theme.css`. Copy it after the base
`fulcra-project-dashboard` CSS and replace its theme placeholders. Do not
add large decorative imagery, autoplay animation, or third-party visual
assets merely to satisfy this requirement. If the project already has a
recognized identity/theme, reuse it; otherwise ask the user for a concise
vibe before rendering.

The chosen theme must be recorded in the curated dashboard configuration or
project status so later agents refresh rather than accidentally reset it.

## Harness-specific panels

### 1. Flight plan

Render every milestone with `passed`, `current`, or `queued` state from
`milestone-progress.md`. Do not leave a previous milestone visually current
just because a static dashboard file was not refreshed.

### 2. Run timeline

Render each terminal run as a dated marker with:

- milestone ID;
- PASS / escalation / decision-required state;
- short evidence summary;
- selected-run detail plus the previous two run summaries;
- horizontal scrolling and zoom for growing history;
- default scroll position at the latest runs.

### 3. Current checkpoint

Prominently render the durable `status-summary.md` sections:

```text
Where we are
Where we're going
Next bearing
```

Include retry mode (`manual` vs. bounded automatic) so a viewer does not
misread an unattended retry as a human decision.

### 4. Open items

Show only current unresolved items:

- open user decision requests from `team/<team>/decision/`;

From fulcradynamics/community-skills, MIT.

More from fulcradynamics/community-skills

Signals

Stars
3
Forks
6
Open issues
4
Last commit (this folder)
Aug 28, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from fulcradynamics

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get fulcra-harness-dashboard running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying fulcra-harness-dashboard?

CallGet help
Cite this page

fulcra-harness-dashboard skill. Agent Mart. https://agentmart.dev/skills/fulcradynamics-fulcra-harness-dashboard (last updated 2026-10-24)