agentleFS
maxwell2732maxwell2732/claudecode-research-harness-workflow/skills/harness-progress/SKILL.md

harness-progress

Skill42 starsChanged 6 days agoMITView on GitHub

Generate a Progress Tracker HTML for non-engineer vibecoders to glance at session progress (cc:WIP / cc:TODO / cc:done counts, percentage, elapsed/estimated minutes, cost so far/estimate, drift alerts). Uses Plans.md as source of truth, renders a single-file HTML with auto-regeneration support. Use when user asks for progress overview, session status snapshot, dashboard, or says: progress tracker, progress check, progress board, dashboard. Do NOT load for: actual implementation, code review, release work.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Only when the --no-open flag is absent (skipped for background regeneration from PostToolUse hook):

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Harness Progress Tracker

Phase 65.4 (Progress Tracker) — 3rd surface of the cognitive-load HTML triplet. Following Plan Brief / Acceptance Demo, this is the third HTML surface, allowing you to see the full picture of the session in progress at a glance on a single page.

Quick Reference

InputAction
/harness-progressGenerate and open the progress snapshot HTML for the current project
/harness-progress --no-openGenerate only (no browser open; for PostToolUse hook)
/harness-progress --out <path>Specify output path (default: out/progress-snapshot.html)

Mission

Generate a single HTML page that allows a non-engineer vibecoder to understand in 3 seconds in a browser how many tasks have been completed in the current session, how far along they are, when they are expected to finish, and what has been spent so far.

Does:

  • Count cc:TODO / cc:WIP / cc:done tasks from Plans.md
  • Calculate progress_pct (completion percentage) (cc:done / total tasks * 100)
  • Display elapsed minutes / estimated total minutes / cost so far / cost estimate
  • Display drift alerts (populated from Phase 65.4.3 onward)

Does NOT (this cycle):

  • Live update via WebSocket / SSE (static HTML, updated by regeneration)
  • Historical comparison with past sessions (separate axis in Phase 65.4.4)
  • Cross-project view for other projects (independent from Phase 65.3)

Schema: progress-snapshot.v1

Full spec: schemas/progress-snapshot.v1.schema.json

schema:        progress-snapshot.v1
project:       <basename of git repo>
current_task:  <first cc:WIP item one-line summary; empty string if none>
progress_pct:  <integer 0-100, cc:done / total tasks * 100 rounded>
todo_tasks:    [{number, title}]    <- cc:TODO only
wip_tasks:     [{number, title}]    <- cc:WIP only
done_tasks:    [{number, title, commit}]   <- cc:done [hash] only, hash is 7 characters
elapsed_minutes:          <int, from state file>
estimated_total_minutes:  <int, from state file>
cost_so_far_usd:          <float, from state file>
cost_estimate_usd:        <float, from state file>
alerts:                    []   <- populated from Phase 65.4.3 onward
generated_at:             <ISO8601 UTC>

Execution Flow

Step 0: Get PROJECT_NAME

PROJECT_NAME="$(basename "$(git rev-parse --show-toplevel)" 2>/dev/null || echo "current")"

Step 1: Build the snapshot

SNAPSHOT_JSON="$(mktemp /tmp/progress-snapshot-XXXX.json)"
bash scripts/progress-snapshot.sh \
  --plans Plans.md \
  --project "$PROJECT_NAME" \
  > "$SNAPSHOT_JSON"

scripts/progress-snapshot.sh (implemented in Phase 65.4.1) parses Plans.md and outputs JSON conforming to the progress-snapshot.v1 schema.

Step 2: Render HTML

OUT_PATH="${OUT_PATH:-out/progress-snapshot.html}"
mkdir -p "$(dirname "$OUT_PATH")"

bash scripts/render-html.sh \
  --template progress \
  --data "$SNAPSHOT_JSON" \
  --out "$OUT_PATH"

Step 3: Open in browser

Only when the --no-open flag is absent (skipped for background regeneration from PostToolUse hook):

bash scripts/plan-brief-open.sh --path "$OUT_PATH"

Cross-project search (default OFF)

The --cross-project-group <name> flag will be added in Phase 65.4.4. In this cycle (65.4.1), it is default OFF; aggregation is for the current project only.

Failure modes

StateBehavior
Plans.md not foundprogress-snapshot.sh exits with exit 1 (clear error message)
Plans.md has no tasksGenerate snapshot with progress_pct: 0, empty arrays (HTML shows "no tasks")
State file (elapsed minutes, etc.) not foundFallback with elapsed_minutes: 0, cost_so_far_usd: 0 (no warning)
git not found / outside git repoFallback with project: "current"

Related

  • harness-plan-brief (Phase 65.1.x) — 1st surface (pre-implementation briefing)
  • harness-accept (Phase 65.2.x) — 2nd surface (acceptance decision)
  • harness-progress (this skill, Phase 65.4.x) — 3rd surface (progress dashboard)
  • 65.4.2 (PostToolUse auto-regen), 65.4.3 (5 types of drift alerts), 65.4.4 (past decision lookup) for feature extensions

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.