Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Sassy-Dog/sassydog-skills/plugin install sassy-dogWrote 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/sassy-dog/sassydog-skills/whats-behind)<a href="https://agentmods.dev/skills/sassy-dog/sassydog-skills/whats-behind"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/whats-behind/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/sassy-dog/sassydog-skills/whats-behind"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/whats-behind.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 | $0.00192 | $0.01542 |
| Opus 5 | $0.00096 | $0.00771 |
| Sonnet 5 | $0.00038 | $0.00308 |
| Haiku 4.5 | $0.00019 | $0.00154 |
Grade A, and why
whats-behind 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 12d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What's Behind
A currency check across every repo in a portfolio: who is lagging their peers on shared versions, and — more usefully — why.
This skill is read-only. It measures and reports; it never edits a pin or opens a PR.
Scope boundary. whats-on-fire covers things that are broken or stalled. This covers things
that merely drift: nothing here is failing today. A product quietly sitting three major versions
behind its siblings never shows up as a fire, which is exactly why it needs its own pass.
1. Pull the drift
PORTFOLIO_ROOT=~/Repos/sassy-dog bash ${CLAUDE_PLUGIN_ROOT}/skills/whats-behind/scripts/pull-version-drift.sh
Emits {repos, actions, toolchains, runners, dependabot, skipped}. MAX_DEPTH defaults to 2 so
multi-repo product groups are covered; depth counts the repo, not its .git.
Exclude archived repos before ranking. The script walks local checkouts, and archived repos
routinely linger on disk long after they stop mattering. Cross-reference the org
(gh repo list <ORG> --json name,isArchived) and drop the archived ones, or the report will
solemnly tell you a dead product is behind. No gh on PATH (cloud sessions): pull the same roster
via the GitHub MCP list-repos capability — the pattern in whats-on-fire's
references/cloud-fallback.md.
2. Rank peer-relative, not absolute
The comparison is against peers, not a registry. If eleven repos run actions/checkout v7 and
one runs v4, that one is behind — regardless of what upstream shipped this week. Peer-relative
ranking also works offline and never nags about a version nobody has adopted.
Read references/interpreting.md for the tiers. The short version:
- Behind the fleet — repo's version is below the portfolio mode for that item. Rank by distance (major gaps first).
- Internally inconsistent — one repo pinning two versions of the same thing. Rank this ABOVE a plain lag: it means the repo has no single source of truth, so any bump is already partial.
- Unmanaged — no Dependabot config, or config that omits
github-actions.
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.
- 12d ago First seen · 124 lines · 192 tokens per session scan A 98bdba1a14c0
whats-behind is a skill published in the GitHub repository Sassy-Dog/sassydog-skills (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 192 tokens to every session and 1,542 once invoked, about $0.0010 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
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
resolving-merge-conflicts
Use when a git merge or rebase reports conflicts and the operation is in progress.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.
analyze
Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots. Use whenever the user asks "how does X work", "map the Y flow", "what are the business rules for Z", "trace the auth path", "explore the codebase…