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/generous-corp/pulp/update-demosnpx skills add Generous-Corp/pulp --skill update-demosgit clone --depth 1 https://github.com/Generous-Corp/pulpWrote 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/generous-corp/pulp/update-demos)<a href="https://agentmods.dev/skills/generous-corp/pulp/update-demos"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/update-demos.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 | $0.00149 | $0.01805 |
| Opus 5 | $0.00075 | $0.00903 |
| Sonnet 5 | $0.00030 | $0.00361 |
| Haiku 4.5 | $0.00015 | $0.00180 |
Grade A, and why
update-demos 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 today.
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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update-demos
When this skill applies
The user asks, in any phrasing, to move the downstream demo/example repos onto a different Pulp SDK. Triggers include:
- "update the demos to the latest SDK"
- "rebuild the examples / demos using the latest version of the SDK"
- "do the new SDK build all the demos still?" / "check the demos still build"
- "bump every consumer's SDK pin to X.Y.Z"
- "open the SDK-update PRs for the demos"
- "republish the demo packages against the new SDK"
These are the Managed SDK Consumer Sweep — one registry of ~15 buildable
downstream repos, driven by pulp minos {sweep,update,publish-runbook}. See the
memory managed-sdk-consumer-sweep for the registry contents and history.
The registry lives in the private planning submodule
The consumer list is planning/sdk-consumers/consumers.yaml. A fresh public
clone will not have it. If any pulp minos sweep|update|publish-runbook prints
consumers registry not found, initialize the submodule first:
git submodule update --init planning
The tools also need PyYAML (python3 -m pip install pyyaml) — they print a clear
install hint if it is absent.
The four-step flow
1. Resolve the target SDK version
"Latest" means the newest published SDK release, not necessarily what this
checkout is at. Resolve a concrete X.Y.Z before doing anything:
pulp sdk available # lists published SDK releases; newest is the target
# or, for the version this source tree builds:
pulp version # SDK + project version of the current checkout
Pin the concrete version for the rest of the flow (e.g. --to 0.640.0). Never
pass a floating latest to update — the pins written into consumer repos must
be exact semver.
2. Verify every consumer still builds — pulp minos sweep
The sweep clones each buildable consumer, configures it against an installed
SDK (find_package(Pulp) + CMAKE_PREFIX_PATH), builds it, measures every
built artifact's min-OS floor, and reports build ok/fail plus floor-vs-SDK-floor
drift. Non-zero exit on any build failure or drift.
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.
- today First seen · 156 lines · 149 tokens per session scan A 40b96dbe9927
update-demos is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 149 tokens to every session and 1,805 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Cut a Symphony release by bumping the committed version, landing it, tagging the merged commit, and verifying the Burrito release workflow. Use when asked to release, tag, or retag Symphony.
changelog
Create changelog files for important commits in a PR.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
refresh-arm-sdk-release
WORKFLOW SKILL — Prepares Azure.ResourceManager SDK refresh pull requests in azure-sdk-for-net. WHEN: "prepare sdk refresh", "refresh Azure.ResourceManager package", "update ARM SDK from autorest tag", "refresh changelog dependencies". INVOKES: git and GitHub pull request tools for branch, commit, push, and PR…