instar-project

instar-project is a skill for Claude Code from JKHeadley/instar. It costs 61 tokens per session (3,700 once invoked), scanned A, original, MIT.

A command interface for registering and managing projects made up of multiple feature specifications. It connects to a local project service to create projects, inspect progress, advance rounds, pause work, resume it, or accept partial results.

In plain words
What is it for?
Use it to create a project from a planning document, check its status, find the next task, run a work round, pause or resume it, and mark work as accepted or abandoned.
Why use it?
It keeps multi-feature work visible and gives developers a defined way to track progress, ownership, drift, and incomplete work.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to create a project from a planning document, check its status, find the next task, run a work round, pause or resume it, and mark work as accepted or abandoned.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jkheadley/instar/instar-project
Install

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.

Any agent
npx skills add JKHeadley/instar --skill instar-project
Clone the repo
git clone --depth 1 https://github.com/JKHeadley/instar

Made for: Claude Code.

Wrote 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.

agentmods badge for instar-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/jkheadley/instar/instar-project/github.svg)](https://agentmods.dev/skills/jkheadley/instar/instar-project)
Your own site
<a href="https://agentmods.dev/skills/jkheadley/instar/instar-project"><img src="https://agentmods.dev/badge/skills/jkheadley/instar/instar-project/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for instar-project

Your own site · 80×15
<a href="https://agentmods.dev/skills/jkheadley/instar/instar-project"><img src="https://agentmods.dev/badge/skills/jkheadley/instar/instar-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,700 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 36
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.03700
Opus 5 $0.00030 $0.01850
Sonnet 5 $0.00012 $0.00740
Haiku 4.5 $0.00006 $0.00370

Measured 9d ago against content hash 5a7111d18f06, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

instar-project scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS -X POST -H "Authorization: Bearer $AUTH" \
.claude/skills/instar-project/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/project — Multi-Spec Project Surface

Spec: docs/specs/PROJECT-SCOPE-SPEC.md § Phase 1.7. A project bundles many feature initiatives into rounds. The dashboard Projects tab, the session-start digest, and the compaction-recovery hook keep them visible. This skill is the user-invocable surface for inspecting and driving them.


Setup — read auth + port once

AUTH=$(python3 -c "import json; print(json.load(open('.instar/config.json')).get('authToken',''))" 2>/dev/null)
PORT=$(python3 -c "import json; print(json.load(open('.instar/config.json')).get('port',4040))" 2>/dev/null)

Every endpoint except /health requires Authorization: Bearer $AUTH.


/project create <plan-doc-path>

Register a new project from a plan-doc markdown file. The plan-doc schema is PlanDocParser's contract (spec § Phase 1.6).

Pre-flight first (no rate-limit cost):

curl -sS -X POST -H "Authorization: Bearer $AUTH" \
  -H "Content-Type: application/json" \
  -d "{\"planDocPath\": \"$(realpath PLAN_DOC.md)\"}" \
  "http://localhost:${PORT}/projects/validate"

Returns 200 {ok, project, children, errors}. Iterate until ok:true.

Then create:

curl -sS -X POST -H "Authorization: Bearer $AUTH" \
  -H "Content-Type: application/json" \
  -d "{\"planDocPath\": \"$(realpath PLAN_DOC.md)\"}" \
  "http://localhost:${PORT}/projects"
  • 201{project, children}.
  • 400 — validation failed; surface each error.
  • 409 — slug already exists.
  • 429 — rate-limited (5 creates/hour per auth token); body includes windowEnds.

/project status [id]

No id — list all projects:

curl -sS -H "Authorization: Bearer $AUTH" "http://localhost:${PORT}/projects"

Render to user: id, title, per-round status summary (e.g. 2/4 complete, 1 in-progress, 1 pending).

With id — fetch the project plus its child items:

curl -sS -H "Authorization: Bearer $AUTH" "http://localhost:${PORT}/projects/<id>"

Read the full file on GitHub · 378 lines

Changes

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.

  1. 9d ago First seen · 378 lines · 61 tokens per session scan A 5a7111d18f06

Subscribe to this mod's changes

instar-project is a skill published in the GitHub repository JKHeadley/instar (79 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 3,700 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories