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 skills add willackerly/rebar --skill rebar-inbox-watchgit clone --depth 1 https://github.com/willackerly/rebarWrote 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.
[](https://agentmods.dev/skills/willackerly/rebar/rebar-inbox-watch)<a href="https://agentmods.dev/skills/willackerly/rebar/rebar-inbox-watch"><img src="https://agentmods.dev/badge/skills/willackerly/rebar/rebar-inbox-watch.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.00414 |
| Opus 5 | $0.00030 | $0.00207 |
| Sonnet 5 | $0.00012 | $0.00083 |
| Haiku 4.5 | $0.00006 | $0.00041 |
Grade A, and why
rebar-inbox-watch 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 6d 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-inbox-watch — arm the peer-inbox watcher
Canonical practice: rebar:practice/inbox-watch (design choices, honest
limitations, variations) — resolve with scripts/rebar-doc.sh rebar:practice/inbox-watch --cat (or rebar doc if the CLI is installed).
This skill is the arming procedure only.
Steps
- Sweep first.
ls -lat inbox/ | head— process any deposits that arrived while no watcher was alive. - Arm the watcher. Run
scripts/inbox-watch.sh <inbox-dir> [<dir>…]through the harness background-monitor facility in persistent mode (Claude Code: the Monitor tool, or a background Bash task). Multi-inbox capable — pass one directory per repo pair you are coordinating. - Default cadence is 30s. Effectively free locally and matched to memo timescales; tighten only during a known live back-and-forth, then return to 30s.
- Act on the emitted lines. One line per new file, shaped
NEW INBOX DEPOSIT: <path>— it lands as a notification mid-task; read and process the memo promptly.
Session-scoped by design
- The watcher dies with the session and must be re-armed at the next
cold start during coordination phases (the
rebar-coldstartskill includes this step). - Silence means "no deposits" only while the watcher is alive — if the monitor died, re-arm before trusting the quiet.
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.
- 6d ago First seen · 35 lines · 59 tokens per session scan A 8e76a16af127
rebar-inbox-watch is a skill published in the GitHub repository willackerly/rebar (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 59 tokens to every session and 414 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-git
Writes commit messages and pull request descriptions for the adk-python repository: Conventional Commits types and scopes, subject lines that say why a change was made, and the linked-issue and testing-plan sections the PR template requires. Use when writing or rewording a commit message, squashing commits before a…
release-readiness-check
Verify all prerequisites are met before a release by checking PRs, CI/CD status, environment health, and blocking issues across GitHub, ArgoCD, and Jira. Use before cutting a release, deploying to production, or during release planning.
review-open-pull-requests
List and analyze all open pull requests across GitHub repositories. Shows review status, CI/CD check results, age, and reviewers. Use when triaging PRs, checking team velocity, or identifying stale reviews that need attention.
ccb-github
Maintain this CCB project's GitHub-facing release and npm publication surface. Use when preparing, publishing, auditing, or fixing CCB releases; updating README.md, README/zh.md, localized README files, CHANGELOG.md, VERSION, package.json, GitHub release notes/assets, repository description/topics, npm registry state…
diff_patch
Unified diff generation, patch application, conflict detection.
git
Git init, commit, diff, log, revert, branch, stash, remote.