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 apigee/devrel --skill skill-findergit clone --depth 1 https://github.com/apigee/devrelWrote 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/apigee/devrel/skill-finder)<a href="https://agentmods.dev/skills/apigee/devrel/skill-finder"><img src="https://agentmods.dev/badge/skills/apigee/devrel/skill-finder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/apigee/devrel/skill-finder"><img src="https://agentmods.dev/badge/skills/apigee/devrel/skill-finder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 170 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Excessive Agency · line 72 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00080 | $0.01901 |
| Opus 5.5 | $0.00032 | $0.00760 |
| Sonnet 5.5 | $0.00016 | $0.00380 |
| Haiku 4.5 | $0.00008 | $0.00190 |
Grade B, and why
skill-finder scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.gemini/config/skills/` (the canonical global skills root). How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-finder
⚠️ Runtime requirements (read this first)
This skill requires its bundled venv wrapper. The Python
scripts depend on cryptography, google-auth, requests, and
pyyaml, which are installed into a per-user venv by the
installer (bin/install-skill-finder.sh). They are not
available to the system python3.
Always invoke scripts via the wrapper, never via bare
python3:
# CORRECT - invokes the venv Python via the wrapper:
${SKILL_DIR}/bin/run-with-venv.sh ${SKILL_DIR}/scripts/<script>.py <args>
# WRONG - system python3 will hit ModuleNotFoundError:
python3 ${SKILL_DIR}/scripts/<script>.py <args>
The Command blocks in this file use the wrapper form. Do not
"simplify" them to python3 … — the scripts will fail with
ModuleNotFoundError: No module named 'cryptography' (or similar)
and the agent will then waste a turn debugging a configuration
issue that doesn't exist.
If the wrapper at ${SKILL_DIR}/bin/run-with-venv.sh is missing,
the skill was installed by a pre-v0.1.4 installer. Re-run
bin/install-skill-finder.sh to regenerate the wrapper. The
scripts themselves also detect this case at startup and emit an
actionable error pointing back here.
This skill has two modes. Choose the one that fits the user's intent:
| User intent | Use this mode | Script |
|---|---|---|
| "What skills are available?" / "Show me the catalog" / "Browse skills" / "What can the agent do via API hub?" | List (browse, no install) | list_skills.py |
| "Find a skill that does X" / "Install a skill for Y" / "Look that up in API hub" (where there is one stated need) | Install (search + verify + install) | find_install.py |
If the user is browsing or exploring, use List first; the user can then ask "install " and you switch to Install with that name as the query.
Runtime dispatch
Both modes ship as one behavioural contract that runs on two runtimes. Pick the invocation path that matches the runtime:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 179 lines · 80 tokens per session scan B 49f076cef89d
skill-finder is a skill published in the GitHub repository apigee/devrel (222 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,901 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
auditing-gcp-iam-permissions
Auditing Google Cloud Platform IAM permissions to identify overly permissive bindings, primitive role usage, service account key proliferation, and cross-project access risks using gcloud CLI, Policy Analyzer, and IAM Recommender.
performing-gcp-security-assessment-with-forseti
Performing comprehensive security assessments of Google Cloud Platform environments using Forseti Security, Security Command Center, and gcloud CLI to audit IAM policies, firewall rules, storage permissions, and compliance against CIS GCP Foundations Benchmark.
implementing-api-threat-protection-with-apigee
Implement API threat protection using Google Apigee policies including JSON/XML threat protection, OAuth 2.0, SpikeArrest, and Advanced API Security for OWASP Top 10 defense.
implementing-gcp-binary-authorization
Implement GCP Binary Authorization to enforce deploy-time security controls that ensure only trusted, attested container images are deployed to Google Kubernetes Engine and Cloud Run.
gcp-cloud-logging
Google Cloud Logging — log search, VPC flow logs, firewall logs, audit logs, log buckets and views. Use when searching GCP logs, investigating denied VPC flow traffic, checking who deleted a VM, analyzing firewall rule hits, or troubleshooting a GCP application error.
notion
Notion workspace integration for searching pages, managing databases, creating postmortems, and exporting RCA findings.