rebar-coldstart

A session-start routine for repositories managed by rebar. It reads key project documents and recent Git history, then checks whether the repository's current state matches its written context.

In plain words
What is it for?
Use it before substantive work in a rebar repository, or after losing context, to review project guidance, recent changes, and cold-start check results.
Why use it?
It reduces mistakes caused by stale instructions or assumptions from an earlier session. It also reveals when the expected automatic startup check did not run.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/willackerly/rebar/rebar-coldstart
Any agent
npx skills add willackerly/rebar --skill rebar-coldstart
Clone the repo
git clone --depth 1 https://github.com/willackerly/rebar

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 470 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.00470
Opus 5 $0.00036 $0.00235
Sonnet 5 $0.00014 $0.00094
Haiku 4.5 $0.00007 $0.00047

Measured 2d ago against content hash 2f8493425d17, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rebar-coldstart 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 2d 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.

.claude/skills/rebar-coldstart/SKILL.md · 33 lines

What it actually says

rebar-coldstart — the session-start ritual

Canonical practice: rebar:practice/session-lifecycle (Session Start section) — resolve with scripts/rebar-doc.sh rebar:practice/session-lifecycle --cat (or rebar doc if the CLI is installed). This skill is a pointer to the ritual, not a replacement for the practice doc.

Steps

  1. Read the cold-start quad: QUICKCONTEXT.md, TODO.md, CLAUDE.md (or AGENTS.md where that is the agent-facing doc), and recent reality — git log --oneline -15.
  2. Look for the hook output. A SessionStart hook (configured in .claude/settings.json) runs scripts/cold-start-checks.sh and injects a <rebar-cold-start>…</rebar-cold-start> block into your first turn. If the block is present, read it — it is harness ground truth, not prose.
  3. No block? Run it yourself. On harnesses without hooks (or before the hook is installed), run scripts/cold-start-checks.sh manually and read its output. Missing block = missing hook; say so.
  4. Cross-check freshness. Compare QUICKCONTEXT claims against git log; if its last-synced date is >1 week old, treat all claims as suspect and verify before acting.
  5. Coordination seats only: if this repo holds a peer inbox/, sweep it first (ls -lat inbox/ | head), then arm scripts/inbox-watch.sh as a persistent background monitor — see the rebar-inbox-watch skill.

Do not start substantive work until steps 1–4 are done.

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. 2d ago First seen · 33 lines · 71 tokens per session scan A 2f8493425d17

Subscribe to this mod's changes

rebar-coldstart is a skill published in the GitHub repository willackerly/rebar (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 71 tokens to every session and 470 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

adk-unit-design

Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to docs/design/{topic}/{unit}/index.md. It describes the code as implemented, not a proposed design, and its reader is a developer about…

google/adk-python · 181 tokens

bigquery-ai-ml

Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).

google/adk-python · 31 tokens

code-review-skill

Reviews code with feedback tailored to the developer's profile in session state.

google/adk-python · 19 tokens

adk-verify-snippets

Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…

google/adk-python · 149 tokens

adk-setup

Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…

google/adk-python · 146 tokens

Apify Automation

Automate web scraping and data extraction with Apify -- run Actors, manage datasets, create reusable tasks, and retrieve crawl results through the Composio Apify integration.

openteams-lab/openteams · 38 tokens