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.
npx agentmods add skills/willackerly/rebar/rebar-feedbacknpx skills add willackerly/rebar --skill rebar-feedbackgit clone --depth 1 https://github.com/willackerly/rebarWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00062 | $0.00531 |
| Opus 5 | $0.00031 | $0.00266 |
| Sonnet 5 | $0.00012 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
rebar-feedback 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.
What it actually says
rebar-feedback — file a feedback item correctly
Canonical reference: rebar:feedback/README (template, processing rules,
disposition lifecycle) — resolve with scripts/rebar-doc.sh rebar:feedback/README --cat (or rebar doc if the CLI is installed).
Reference it; do not restate it.
First: where does this filing go?
- Working in the rebar repo itself (it has
feedback/): file locally, steps below. - Working in an adopter repo (no
feedback/directory): the feedback is about rebar, so it belongs upstream — useask rebar featurerequest "<the situation>"(MCP/ASK), or write the file into your rebar checkout'sfeedback/directory. Do not create afeedback/dir in the adopter repo for rebar-bound items.
Steps (rebar repo)
- Read the canonical reference (
rebar:feedback/README, above) and skim one recentfeedback/*.mdfile for the house voice before writing anything. - Check the gate: the situation must be real, not hypothetical — a
specific scenario you actually hit (
rebar:charter§3, gate 3: concrete use case). "Would be cool if…" does not qualify; do not file. - Create the file:
feedback/YYYY-MM-DD-<slug>.md(today's date, short kebab-case slug). - Fill the required header fields:
Date,Source,Type,Status(start atproposed),Template impact,From(agent/model, project, date — provenance matters). - Body: What Happened / What Was Expected / Suggestion. Be concrete. Point at files with one-line pointers rather than restating their content.
Do not edit feedback/INVENTORY.md or move files into feedback/processed/
— triage and disposition are maintainer-owned (see "Processing Feedback" in
rebar:feedback/README).
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.
- 2d ago First seen · 41 lines · 62 tokens per session scan A 78c8ef793837
rebar-feedback is a skill published in the GitHub repository willackerly/rebar (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 62 tokens to every session and 531 once invoked, about $0.0003 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.
Other skills, from other repositories
adk-sample-creator
Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use. Use when the user wants to add a sample or example demonstrating a feature or agent pattern (dynamic nodes, fan-out/fan-in, a standalone…
xlsx
Read, create, or edit Excel spreadsheets (.xlsx/.xlsm) — sheet data, formulas, styles, charts, multi-sheet workbooks — and bulk .csv/.tsv tables; use whenever a spreadsheet is the input or the deliverable (extract/analyze data, add columns/formulas/formatting/charts, clean messy tables, build from scratch), but not…
adk-debug
Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the adk run CLI and the adk web dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs…
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…
text-skill
A text processing skill that formats strings using shell scripts.
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…