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 CiscoDevNet/essentials --skill ess-my-groupsgit clone --depth 1 https://github.com/CiscoDevNet/essentialsWrote 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/ciscodevnet/essentials/ess-my-groups)<a href="https://agentmods.dev/skills/ciscodevnet/essentials/ess-my-groups"><img src="https://agentmods.dev/badge/skills/ciscodevnet/essentials/ess-my-groups/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/ciscodevnet/essentials/ess-my-groups"><img src="https://agentmods.dev/badge/skills/ciscodevnet/essentials/ess-my-groups.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00137 | $0.02112 |
| Opus 5.5 | $0.00055 | $0.00845 |
| Sonnet 5.5 | $0.00027 | $0.00422 |
| Haiku 4.5 | $0.00014 | $0.00211 |
Grade A, and why
ess-my-groups scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
My Groups
The user keeps a small file of users (with nicknames, an email, and handles on services such as GitHub or Webex) and named groups of those users. This skill turns "my pod" or "Ada" into those users, and edits the file when the user asks, so they never touch TOML themselves. It only answers "who"; the task that needs the people (a search, a message, a review) is done with whatever tool fits it.
SKILL_DIR below is the absolute path of the directory containing this SKILL.md.
Do not use a repo-relative path; the skill may be installed outside the repo.
uv run --script "$SKILL_DIR/scripts/my_groups.py" resolve "my pod"
The file
${XDG_CONFIG_HOME}/ess-my-groups/groups.toml. XDG_CONFIG_HOME counts only when it
is absolute; otherwise the path is ~/.config/ess-my-groups/groups.toml.
ESS_MY_GROUPS_FILE overrides both. my_groups.py path prints the resolved path.
Read references/groups-format.md only if you need the schema, for example when the user wants to edit the file by hand.
Resolve before acting
When a request names a group or a user by nickname:
- Run
resolvewith every name from the request, in one call:uv run --script "$SKILL_DIR/scripts/my_groups.py" resolve "my pod" Ada - Read the output: a JSON array of JSContact
Cards.
- Each group you named comes first, as a Card with
"kind": "group". Itsmembersholds theuidof every user in the group, nested groups included. - Then comes one Card per user, deduplicated across overlapping and nested
groups. Its
uidisuser:<key>, ormailto:<address>for an email with no user entry. It may havename.full,nicknames,emails(each with anaddress), andonlineServices, where each entry has aservice, such asgithub, and auser, the handle. A user may have several handles on one service; use all of them.
- Each group you named comes first, as a Card with
- Handle gaps before doing the task, not after:
- stderr lists
warning: unresolved name '…'for bare names with no user entry. Say so, and ask whether to add them (with an email) or skip them. - Check each member for the exact identifier the task needs: an email, or a handle on that particular service. Having one doesn't stand in for the other; a member with an email but no GitHub handle can't be found by a GitHub search. Name every member who lacks it in your answer, and offer to add it.
- stderr lists
- If
resolvefails with "No user or group named …", show the "Did you mean" hint if there is one, and otherwise ask the user who they meant. Don't guess. If it fails because a name matches more than one entry, retry with theuser:orgroup:form it lists. - Then do the task with the resolved emails and handles.
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.
- 2d ago First seen · 153 lines · 137 tokens per session scan A 04d107f5450a
ess-my-groups is a skill published in the GitHub repository CiscoDevNet/essentials (7 stars, last pushed 3d ago), licensed Apache-2.0. It adds 137 tokens to every session and 2,112 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-11-04.
ess-my-groups compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ess-my-groupsCiscoDevNet/essentials | Skill | 7 | 3d ago | Apache-2.0 | A | 137 | Claude Code, Codex |
| writing-blogsappwrite/appwrite | Skill | 58k | today | BSD-3-Clause | A | 64 | Cursor |
| create-announcementappwrite/appwrite | Skill | 58k | today | BSD-3-Clause | A | 0 | Cursor |
| auditing-seoappwrite/appwrite | Skill | 58k | today | BSD-3-Clause | A | 52 | Cursor |
| reviewing-blogsappwrite/appwrite | Skill | 58k | today | BSD-3-Clause | A | 55 | Cursor |
| dashboard-chat-best-practicesvercel/eve | Skill | 5.8k | today | Apache-2.0 | A | 84 | Codex |
| eve-chat-template-evevercel/eve | Skill | 5.8k | today | Apache-2.0 | A | 75 | Codex |