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 instructions/omrigm/standup/claude-mdgit clone --depth 1 https://github.com/OmriGM/standupWhat 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 | $0.00972 | $0.00972 |
| Opus 5 | $0.00486 | $0.00486 |
| Sonnet 5 | $0.00194 | $0.00194 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
standup CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on standup
One Python file, hooks/standup.py, plus the manifests around it. No dependencies beyond
the standard library, and that is a feature worth protecting.
Before every commit
python3 hooks/standup.py self-check # asserts the scoring and parsing logic
python3 .github/check_manifests.py # asserts the manifest invariants
HOME="$(mktemp -d)" python3 hooks/standup.py report # must render from an empty history
CI runs all three, plus the version check below. Run them locally first.
Bump the version. Every time.
If you change anything under hooks/, commands/ or .claude-plugin/, bump
version in .claude-plugin/plugin.json in the same commit.
Installs are cached per version. A change pushed under an unchanged version reaches
nobody, and it looks like it worked. This has already happened: three commits shipped
under a stale 0.1.1 and no user ever saw them.
.github/check_version_bumped.py fails the build if you forget. Do not work around it.
Everything after the bump is automatic. Push to main and the release workflow tags the
commit and publishes a GitHub Release. Never create a release by hand.
Traps this codebase has already fallen into
Each of these shipped once. They are cheap to reintroduce and hard to spot.
- CSS animation
fill-mode: bothoutranks:hover. A filled animation keeps applying its finaltransformandopacityforever, beating any normal declaration. It silently killed the card hover lift and the dimming of hidden cards. Usebackwardsfor staggered entrances, so the delay is covered and the property is released afterwards. @media (prefers-reduced-motion)must stay at the very end of the stylesheet. At equal specificity the later rule wins, so overrides placed above the rules they override do nothing at all.- CSS beats SVG presentation attributes.
.ico { fill: currentColor }overridesfill="none"on a symbol and renders outline icons as solid shapes. Style them with a class instead. - Python 3.9 is the floor and it is tested in CI. No backslashes inside f-string
expressions, which only became legal in 3.12. A local
ast.parse(feature_version=(3,9))does not catch this; only a real 3.9 interpreter does. - Never declare
hooks/hooks.jsonundermanifest.hooks. That path loads automatically, and naming it again makes Claude Code load it twice and refuse the plugin.manifest.hooksis only for hook files outside the standard location. - Round components, not the total. The impact score is the sum of the parts its tooltip prints. Rounding the total instead makes badges that cannot be added up.
- The tool must never record its own runs.
report --summariesshells out toclaude, which leaves a transcript. It is skipped viaSENTINEL, both on write and on read.
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 · 77 lines · 972 tokens per session scan A 0e63d0016586
standup CLAUDE.md is an instructions file published in the GitHub repository OmriGM/standup (1 stars, last pushed 24d ago), licensed MIT. It adds 972 tokens to every session, about $0.0049 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 instructions, from other repositories
economist-style-guide-plugin CLAUDE.md
Instructions for TAJD/economist-style-guide-plugin, covering claude.md, project overview, repository structure, how the plugin works and publishing.
ai-business-skills CLAUDE.md
Instructions for minhnv0807/ai-business-skills, covering claude.md — fullstack marketing skills, identity, nguyen tac cot loi, cach su dung skill and tu dong nhan dien.
Product-Marketing-Skills CLAUDE.md
Instructions for stefanoskarakasis/Product-Marketing-Skills, covering claude.md, versioning & releases, release procedure (manual, until ci enforcement exists) and after any repo change.
heimdall AGENTS.md
Instructions for randomittin/heimdall, covering working in the heimdall repo, the rules that actually block you, environment, conventions and heimdall — this repo is gated.
skills CLAUDE.md
Instructions for skrrt-sh/skills, covering git workflow and repository structure.
ai-plugins AGENTS.md
Instructions for openEHR/ai-plugins, covering ai-plugins, repository purpose, structure, key conventions and development.