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/osouthgate/agent-plus/agent-plus-upgradenpx skills add osouthgate/agent-plus --skill agent-plus-upgradegit clone --depth 1 https://github.com/osouthgate/agent-plusWrote 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/osouthgate/agent-plus/agent-plus-upgrade)<a href="https://agentmods.dev/skills/osouthgate/agent-plus/agent-plus-upgrade"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus/agent-plus-upgrade.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 | $0.00127 | $0.03146 |
| Opus 5 | $0.00063 | $0.01573 |
| Sonnet 5 | $0.00025 | $0.00629 |
| Haiku 4.5 | $0.00013 | $0.00315 |
Grade A, and why
agent-plus-upgrade 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 5d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-plus-upgrade
Trigger doctrine for when to check whether the agent-plus framework itself
is out of date, and how to offer the fix — same shape as
agent-plus-installer, but for the upgrade
path instead of the install path. No new mechanism: agent-plus-meta upgrade-check and agent-plus-meta upgrade already exist, fully built, with
a frozen v0.13.5 JSON contract (snooze ladder, .bak rollback, migrations,
in-process post-upgrade doctor gate).
This skill exists because, until 2026-07-07, nothing ever called
upgrade-check — it wasn't wired into any nextSteps chain and no skill
triggered it, so every installed user silently drifted from the latest
release with no signal. Since then, envcheck's clean-path nextSteps also
appends upgrade-check as a suggested command (see the root README's funnel
table) — that closes reach for sessions that run the standard bootstrap,
but a nextSteps entry is only ever a suggested string, never an automatic
action, and it only fires when envcheck itself runs with nothing missing.
This skill still owns the judgment neither the funnel nor the CLI provides
on its own: deciding whether an upgrade is actually worth surfacing
(verdict / config.update_check / snooze.active gating), presenting the
right one of the four choices, and driving the silent_upgrade fast path
correctly. The two are complementary, not redundant — funnel widens reach,
this skill supplies the decision.
The probe
agent-plus-meta upgrade-check
Cheap and safe to run proactively: reads a cache first (TTL 60min when
up to date, 720min once an upgrade is already known to be available), falls
back to a capped ≤3s network GET of a single-root VERSION file, and
fails silently on any network error (never raises, never blocks). Read
the JSON envelope's gating fields before deciding whether to say anything:
| Field | Meaning | Your action |
|---|---|---|
verdict |
up_to_date | upgrade_available | unknown (just_upgraded is reserved in the frozen contract but not currently emitted by cmd_upgrade_check — don't branch on it) |
Only upgrade_available is worth surfacing. |
config.update_check |
false means the user already chose "Never ask again" |
If false, stay silent — don't surface anything, don't re-probe later this session either. |
snooze.active |
true means the user is inside an active 24h/48h/7d/never snooze window |
If true, stay silent even when verdict == upgrade_available. |
errors |
Non-empty on network failure | Stay silent; this probe is best-effort by design. |
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.
- 5d ago First seen · 231 lines · 127 tokens per session scan A 21bf5a49138f
agent-plus-upgrade is a skill published in the GitHub repository osouthgate/agent-plus (4 stars, last pushed 1mo ago), licensed MIT. It adds 127 tokens to every session and 3,146 once invoked, about $0.0006 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 skills, from other repositories
notify-user
Telegram comms playbook for Antigravity — when and how to reply, ack long work, present choices, and delegate to other agents. Use whenever you're paired to a Telegram chat via the telegram-agy MCP server and need to talk back to the user. The chat is your only signal channel — terminal output never reaches the user.
rag-your-code
Index and search the current codebase with local, explainable RAG records.
slack-cli
Complete Slack Web API CLI — 201 methods across 29 command groups. Every public endpoint. Agent-friendly JSON output. Auto-generated from the official OpenAPI spec + @slack/web-api SDK. Use when: sending messages, reading channels, adding reactions, managing files, searching, pins, bookmarks, reminders, user groups…
slack-messages
Send Slack messages to channels or users via the elnora-slack CLI. Resolves channel/user IDs from the cached workspace reference, formats messages, handles threads and DMs, and enforces a draft-and-approve gate before anything is sent. TRIGGERS: "send slack", "slack message", "post on slack", "message on slack", "tell…
compounded-author
Use this skill when you have just completed a non-trivial task (more than 3 tool calls, novel approach, recovery from a dead end) and are considering whether to save the procedure as a reusable skill via compounded; OR in RULE MODE when the user corrected your approach and the correction encodes a generalizable…
compounded-verifier
Use this skill ONLY when invoked as the skill-verifier subagent by compounded's Stop hook. This is the rubric for deciding whether a proposed skill should graduate to .verified or move to .rejected/ based on its replayability against a just-completed task. Do not invoke this skill in normal sessions.