Automated summary
Deterministically updates status, last_flow, and updated_at in .runs/index.json using a dedicated shim.
Strengths
- Deterministic writes ensure stable diffs
- Idempotent – safe to run multiple times with same arguments
- Strict contract with 'ok' output and exit code 0 on success
Limitations
- Cannot create the index.json file (fails if missing)
- Restricted to specific agents (run-prep, cleanup) – narrow scope
- Only updates status, last_flow, updated_at – other fields owned elsewhere
When you need to update a run's state in the index file after a cleanup or preparation step.
If you need to create or modify fields other than status, last_flow, or updated_at, or if the index.json does not exist yet.
Security analysis
SafeThe skill invokes a local bash script to update a JSON file with deterministic writes. No external downloads, exfiltration, or destructive commands. Usage is restricted to specific agent roles, and the script never creates the index file, only updates existing ones. No elevated risk.
No concerns found
How this analysis is madeExamples
Update the status of run 'feat-auth' to VERIFIED with last_flow 'signal' in .runs/index.jsonSet status 'PENDING' and last_flow 'build' for run 'hotfix-123' in .runs/index.jsonname: runs-index description: "Update index.json status. Use for: upsert index.json, update status/last_flow/updated_at. Deterministic writes - stable diffs, no creation. Use only in run-prep and *-cleanup agents. Invoke via bash .claude/scripts/demoswarm.sh index upsert-status." allowed-tools: Bash, Read, Write
Runs Index Skill
Deterministic updates to .runs/index.json. Write-bearing but with minimal surface.
Invocation
Always invoke via the shim:
bash .claude/scripts/demoswarm.sh index upsert-status [options]
Do not set PATH or call helpers directly. The shim handles resolution.
Operating Invariants
Repo root only
- Assume working directory is repo root.
- All paths are repo-root-relative.
Minimal ownership
This skill only updates:
statuslast_flowupdated_at
Other fields (canonical_key, issue_number, pr_number, etc.) are owned by run-prep, signal-run-prep, and gh-issue-manager.
Stable diffs
- Upsert by
run_id(update in place, not append) - Preserve existing ordering
- Output is sorted for stable git diffs
Allowed Users
Only these agents may use this skill:
run-prepsignal-run-prepsignal-cleanupplan-cleanupbuild-cleanupgate-cleanupdeploy-cleanupwisdom-cleanup
Command Reference
| Command | Purpose |
| --------------------- | ------------------------------- |
| index upsert-status | Update run status in index.json |
Quick Example
# Update index after signal cleanup
bash .claude/scripts/demoswarm.sh index upsert-status \
--index ".runs/index.json" \
--run-id "feat-auth" \
--status "VERIFIED" \
--last-flow "signal" \
--updated-at "$(bash .claude/scripts/demoswarm.sh time now)"
# stdout: ok
Contract Rules
- stdout:
okon success, error message on failure - exit code:
0on success, non-zero on failure - Idempotent: Running twice with same args produces same result
- No creation: If
.runs/index.jsondoesn't exist, fail (run-prep owns creation)
Index Schema Reference
{
"version": 1,
"runs": [
{
"run_id": "feat-auth",
"canonical_key": "gh-456",
"task_key": "feat-auth",
"task_title": "Add OAuth2 login",
"issue_number": 456,
"pr_number": null,
"updated_at": "2025-12-11T22:15:00Z",
"status": "VERIFIED",
"last_flow": "signal"
}
]
}
This skill only updates: status, last_flow, updated_at.
For Agent Authors
In cleanup agents:
- Use
runs-indexfor index updates (no inline jq) - Handle missing index — if
.runs/index.jsonis missing, add a blocker and do not create it - Use
runs-derivefor reading — this skill is write-only
Example pattern in cleanup agent:
# Get current timestamp
TIMESTAMP=$(bash .claude/scripts/demoswarm.sh time now)
# Update index
bash .claude/scripts/demoswarm.sh index upsert-status \
--index ".runs/index.json" \
--run-id "$RUN_ID" \
--status "$STATUS" \
--last-flow "signal" \
--updated-at "$TIMESTAMP"
Installation
The Rust implementation is preferred. Install to repo-local directory:
cargo install --path tools/demoswarm-runs-tools --root .demoswarm
The shim will automatically resolve in order:
.demoswarm/bin/demoswarm(repo-local install, preferred)demoswarmon PATH (global install)cargo runfallback (dev environments)- Python fallback (legacy)
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/runs-index-update-mm5t8b5v/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/runs-index-update-mm5t8b5v' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/runs-index-update-mm5t8b5v/download' --output '.skill-downloads/runs-index-update-mm5t8b5v/SKILL.md.part' && mv '.skill-downloads/runs-index-update-mm5t8b5v/SKILL.md.part' '.skill-downloads/runs-index-update-mm5t8b5v/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Bash, Read, Write
Original excerpt: Installation
The Rust implementation is preferred. Install to repo-local directory:
cargo install --path tools/demoswarm-runs-tools --root .demoswarm
The shim will automatically resolve in order:
.demoswarm/bin/demoswarm(repo-local install, preferred)demoswarmon PATH (global install)cargo runfallback (dev environments)- Python fallback (legacy)
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/runs-index-update-mm5t8b5v/SKILL.md' && test -s '.skill-downloads/runs-index-update-mm5t8b5v/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/runs-index' && cp -R '.skill-downloads/runs-index-update-mm5t8b5v' '.claude/skills/runs-index'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/runs-index-update-mm5t8b5v'openskills read 'runs-index-update-mm5t8b5v'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/runs-index-update-mm5t8b5v/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.