Borrowing it
Nothing to install: this file belongs to Koroqe/OPOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Koroqe/OPOS/main/.claude/skills/check-for-updates/SKILL.mdgit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/check-for-updates)<a href="https://agentmods.dev/skills/koroqe/opos/check-for-updates"><img src="https://agentmods.dev/badge/skills/koroqe/opos/check-for-updates/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/koroqe/opos/check-for-updates"><img src="https://agentmods.dev/badge/skills/koroqe/opos/check-for-updates.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 | $0.00029 | $0.01680 |
| Opus 5 | $0.00015 | $0.00840 |
| Sonnet 5 | $0.00006 | $0.00336 |
| Haiku 4.5 | $0.00003 | $0.00168 |
Grade A, and why
check-for-updates 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
check-for-updates
When to use
Invoked automatically as step 1 of task-register, task-update, task-complete, and (v0.8.1) as part of the chief-of-staff First-touch protocol on session open — so consumers whose daily rhythm does not go through the task-lifecycle skills still get the notice. Adopters can invoke manually via /check-for-updates --force to force a fresh check, or /check-for-updates --include-prerelease to consider pre-release tags.
The skill is cheap (one gh api call cached 6h) and silent unless an update is available — it does not block or interfere with the parent skill's normal flow.
Inputs
force(optional bool; default false): bypass the 6h cache and check upstream now.include_prerelease(optional bool; default false): include pre-release tags in the latest-check.
Steps
- Resolve repo root via
git rev-parse --show-toplevel. - Read
<repo-root>/.copier-answers.yml. Extract_commit(current pinned tag) and_src_path(upstream URL). If missing: print one-line warning (.copier-answers.yml not found — was this repo scaffolded with copier?) and exit 0. Do NOT fail the parent skill. - Read
<repo-root>/.claude/.last-update-check. If timestamp < 6h old AND--forceis false, exit 0 silently. Skip history write in this fast path (no value, just bloat — see step 8). - Classify
_src_pathand resolve the upstream source. Four shapes are recognised:- Remote GitHub —
gh:owner/repo,[email protected]:owner/repo(.git),https://github.com/owner/repo(.git). Extract<owner>/<repo>(strip prefix, strip trailing.git). This is the portable, recommended shape. - Local path (v0.8.1) — an absolute or relative filesystem path that exists and contains a
.gitdirectory (e.g./home/agent/workspace/OPOS, produced when the consumer was scaffolded from a local clone viacopier copy <path> ...). Resolve the latest tag directly from that clone:git -C "<path>" tag --sort=-v:refname | grep -v -- '-' | head -1(dropgrep -v -- '-'when--include-prerelease). Print a one-line portability warning every time this branch is taken:⚠️ .copier-answers.yml _src_path is a local path (<path>) — updates only work on this machine. Consider re-pointing it to gh:<owner>/<repo>.(The warning is deliberately loud: a local_src_pathsilently breaks the update loop on every other machine, CI runner, or second consumer.) - Local path that does NOT exist — print
⚠️ .copier-answers.yml _src_path (<path>) does not exist on this machine — update loop is broken here; re-point _src_path to the upstream GitHub URL.and exit 0. This IS a meaningful event: write the history entry (step 8) withoutcome: failure. - Anything else (unparseable) — print
⚠️ check-for-updates: cannot parse _src_path '<value>' — expected gh:owner/repo, a GitHub URL, or a local clone path.and exit 0; write the history entry withoutcome: failure. Never fail silently on a parse error — a broken checker must be distinguishable from "you are up to date" (v0.8.1: this was the root cause of a consumer sitting two releases behind with no signal).
- Remote GitHub —
- Fetch the latest tag (Remote GitHub shape only; the local-path shape already resolved it in step 4):
- Default (no
--include-prerelease):gh api repos/<owner>/<repo>/releases --jq '[.[] | select(.prerelease == false)] | first | .tag_name'— fetches the full list, filters out prereleases, takes the first (newest). No leading slash on the endpoint: under Git-Bash/MSYS on Windows a leading/repos/...is rewritten to a Windows path (C:/Program Files/Git/repos/...) andgh apifails with "invalid API endpoint". - With
--include-prerelease:gh api repos/<owner>/<repo>/releases/latest --jq '.tag_name'. - On network/rate-limit/auth failure: silent exit 0 (no history entry — silent skips are not meaningful events). Note the distinction from step 4: network failures are transient and silent; configuration failures (unparseable / non-existent
_src_path) are permanent and loud.
- Default (no
- Compare the latest tag to
_commit. If they differ, print to stdout:ℹ️ OPOS-core <new-tag> is available (you're on <current>). Run /sync-from-core to apply. - Write
<repo-root>/.claude/.last-update-checkwith the current ISO timestamp + the latest tag observed. Format:YYYY-MM-DDTHH:MM:SSZ <tag>on one line. - Write history entry ONLY IF (a) an update was found in step 6, OR (b)
--forcewas passed. Skip on silent "no update" runs to avoid fillinghistory/with hundreds of empty entries per week. This is the conditional-history-write rule documented explicitly.
What ships with it
2 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.
- 8d ago First seen · 61 lines · 29 tokens per session scan A 064d27377ed3
check-for-updates is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 7d ago), licensed MIT. It adds 29 tokens to every session and 1,680 once invoked, about $0.0001 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
skill-compiler
Automatic solved-to-skill compiler — detects novel task completions and autonomously drafts new SKILL.md files. Stolen from Hermes Agent's learning loop (NousResearch, 2026-05-11).
om-build-workflow
Build or extend standalone business workflows, activities, event triggers, durable user tasks, compensation, output paths, idempotency, and live progress. Use for "add workflow", "custom activity", "CALLAPI", "approval task", "workflow progress", or "zbuduj workflow".
context-compactor
9-section context compression with analysis scratchpad. Adapted from Claude Code's /compact system (2026-03-31).
daemon-loop
Autonomous recurring agent tasks — converts workflows into persistent background daemons that run on intervals. Stolen from Boris Cherny's Claude Code /loop pattern (2026-03-31).
trade-journal-analyzer
Unified post-trade analytics: journal pattern extraction + drawdown classification. Absorbs: drawdown-classifier.
Deep Research Loop
Multi-step web research, compilation, and synthesis workflow. Scrapes multiple sources, cross-references claims, and produces a structured research brief.