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/intel-canarynpx skills add Generous-Corp/pulp --skill intel-canarygit 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/intel-canary)<a href="https://agentmods.dev/skills/generous-corp/pulp/intel-canary"><img src="https://agentmods.dev/badge/skills/generous-corp/pulp/intel-canary.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 | $0.00095 | $0.03403 |
| Opus 5 | $0.00048 | $0.01702 |
| Sonnet 5 | $0.00019 | $0.00681 |
| Haiku 4.5 | $0.00010 | $0.00340 |
Grade A, and why
intel-canary 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intel canary skill
Pulp ships macOS arm64 as usable and macOS x86_64 / universal as
experimental. This skill owns the machinery that keeps the Intel story from
silently regressing. The full design, tiering, and the honest catch/miss list
live in docs/guides/intel-support.md — read it first.
The Tier-1 Rosetta lane measures logic, not speed
intel-portability.yml runs x86_64 binaries under Rosetta on an arm64 runner, at
roughly a third of native speed. Anything asserting a wall-clock budget therefore
reports the emulator.
That lane went red for seven consecutive runs on exactly three of 16,314 tests,
all timing-bound: heritage-performance (labels performance quality-lab), a
CompiledTempoMap randomized-map Timeout, and process-deadline-selftest.
None was an x86_64 defect.
The cause was a drifted exclusion list: build.yml excludes
performance|bench|quality-lab on PR runs, this lane excluded only
validation|slow. When adding a timing-sensitive label or a deadline test, update
both — and remember --repeat until-pass:2 only absorbs a single flake, so a
consistently slow test fails twice and reds the lane.
A red here is advisory and blocks nothing, which is precisely why it can sit red for days while burning ~52 minutes of hosted macOS per triggering PR.
What this skill covers
tools/scripts/intel_canary_lint.py— the Tier-0 static lint (5 classes).tools/scripts/intel_canary_allowlist.txt— its exemption list.tools/scripts/test_intel_canary_lint.py— the lint's self-test.- The
PULP_INTEL_CANARYoption in the rootCMakeLists.txt. - The Tier 0-4 workflows:
build.yml(canary step),intel-portability.yml(Tier 1 advisory PR lane),nightly-intel.yml(Tier 2), and theuniversal-crosscheckjob innightly-intel.yml(Tier 3, nightly), plus the dedicated physical Intel selector and supervisor (Tier 4, advisory).
Note: the Tier-3 universal check only validates a universal build — it publishes
nothing, and the release ships THIN per-arch binaries. It lives in
nightly-intel.yml's universal-crosscheck job (nightly), NOT on the release
path: a redundant canary for an artifact we do not ship must never be able to
block or starve a release. intel-portability.yml covers Intel at PR time.
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 · 227 lines · 95 tokens per session scan A 6c3e3ba52c21
intel-canary is a skill published in the GitHub repository Generous-Corp/pulp (16 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 3,403 once invoked, about $0.0005 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
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
atmos-cache
Atmos caching: CI cache configuration and commands, GitHub Actions cache integration, Terraform registry cache mirror/list/prune/stats/trust, and cache modernization guidance.