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 Sassy-Dog/sassydog-skills --skill recapgit clone --depth 1 https://github.com/Sassy-Dog/sassydog-skillsWrote 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/recap)<a href="https://agentmods.dev/skills/sassy-dog/sassydog-skills/recap"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/recap/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/recap"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/recap.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 | $0.00121 | $0.00939 |
| Opus 5 | $0.00060 | $0.00469 |
| Sonnet 5 | $0.00024 | $0.00188 |
| Haiku 4.5 | $0.00012 | $0.00094 |
Grade A, and why
recap 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 11d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recap
One retrospective report of the session just worked: what happened, what it revealed, and what to do next — the same shape every time, so the user can scan it instead of re-reading the session.
Acting principle: a recap is evidence, not memory. Report only what was actually observed in
this session; anything uncertain renders as uncertain, never inferred — a confident summary built
on unverified claims reads exactly like a real one. Before asserting a terminal state ("merged",
"closed", "landed"), re-check it with a quick read (gh pr view, gh issue view) if the session's
last observation of it is stale.
1. Gather
Walk the session once and sort every event into exactly one bucket:
- Work completed — things that changed state and finished: merged PRs, pushed commits, config or infrastructure mutations, external actions (routine/trigger updates, secrets set). Each item keeps its evidence: PR number, commit SHA, run or session id, or link.
- What surfaced — findings the session produced that required no action yet: gotchas hit, diagnoses made, signals noticed (a flaky test, a coverage gap, a doc mismatch). One line each on why it matters.
- Issues we should file — the subset of surfaced signals with NO tracking issue anywhere. Each
gets a proposed title, suggested labels, and a one-line rationale — enough that filing it later
is mechanical. Check
gh issue list --searchbefore proposing; a signal that is already tracked belongs under "what surfaced" with its issue number instead. - Immediate next steps — actions, not states. "PR #13 awaiting merge" is a state; "Merge PR
#13 — green and waiting on a human press" is a step. Order by priority; when the step is a
one-liner, include the literal command (
take #99,gh pr merge 13 --auto).
In-flight work that is still running (a watcher, an unfinished agent, an unmerged PR) is a next step, never "completed".
2. Render
Output exactly this shape, inline as markdown:
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.
- 11d ago First seen · 84 lines · 121 tokens per session scan A 2ad22b602dc1
recap is a skill published in the GitHub repository Sassy-Dog/sassydog-skills (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 121 tokens to every session and 939 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
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
ensure-pipelines-host
Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs. Detects host state via the same resolution order as the Power Apps UI (org-db setting → BAP env metadata → default-custom-host setting); if any existing host (Platform or Custom) is found, uses it. If no host…