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/assess-it)<a href="https://agentmods.dev/skills/sassy-dog/sassydog-skills/assess-it"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/assess-it/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/assess-it"><img src="https://agentmods.dev/badge/skills/sassy-dog/sassydog-skills/assess-it.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 | $0.00131 | $0.02321 |
| Opus 5 | $0.00066 | $0.01161 |
| Sonnet 5 | $0.00026 | $0.00464 |
| Haiku 4.5 | $0.00013 | $0.00232 |
Grade A, and why
assess-it 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess-It
Turn a whole repository into a deduped, evidence-backed, PR-sized GitHub Issue backlog under one tracking Epic — by fanning out specialized review agents, adversarially verifying their findings, and filing only what survives.
Repo-agnostic. Works on any GitHub repo. Operates on one repo per run (the current working dir unless a target is given). A periodic routine loops multiple repos — that lives outside this skill.
Default = preview, not file. Filing issues is outward-facing and hard to undo. Always present the proposed Epic + child issues for approval and file only after the user confirms. Never create issues silently.
Core Principle
A finding only earns an issue if it has concrete file:line evidence, survives an adversarial second look, and is not already tracked by an existing issue. Everything else is noise — drop it. One issue = one coherent PR's worth of work.
Workflow
Follow the five phases. Full dispatch details, the finding schema, and exact gh commands live in the reference files — read them when you reach that phase.
Phase 0 — Scope & detect (you, the main agent)
- Resolve the target repo (cwd or the path/arg given). Confirm a GitHub remote:
gh repo view --json nameWithOwner,defaultBranchRef. - Detect stack(s) by globbing manifests:
package.json,*.csproj,Cargo.toml,pubspec.yaml,*.tf/*.bicep,Dockerfile,.github/workflows/, Nx/Bun/tRPC config. This decides which review agents to dispatch. - Build the dedupe index (used in Phase 2 and Phase 4):
gh issue list --state open --limit 500 --json number,title,labels,body(also pull recently-closed for context). Keep it in memory for the whole run.
Phase 1 — Fan out (parallel review agents)
Dispatch the relevant sassy-dog:*-reviewer agents in a single message with multiple Agent tool calls so they run concurrently. Skip domains with no signal (no IaC → skip infra-platform-reviewer). Give each agent the repo path, the detected stack, and its scope. Each returns only the JSON object {"findings": [...]} as final text, with findings in the shared schema and mandatory file:line evidence. Accept returned only for a usable envelope per orchestration.md; {"findings": []} is completed-empty, while missing or malformed results are no report, never clean. Unwrap usable findings for Phase 2 verification.
What ships with it
3 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.
- 3d ago Changed f1874c2eb997
- 12d ago First seen · 100 lines · 131 tokens per session scan A 0fe5a07be3cf
assess-it is a skill published in the GitHub repository Sassy-Dog/sassydog-skills (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 131 tokens to every session and 2,321 once invoked, about $0.0007 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
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
done-blocked
Reusable reporting contract for any agent that hands work back to the pipeline. Forces ONE of two terminal statuses (DONE or BLOCKED) with a specific evidence shape. Stops vague "probably finished" and "kind of stuck" verdicts.
outcome-roadmap
Transform an output-focused roadmap (feature list) into an outcome-focused one. Rewrites initiatives as outcome statements reflecting user and business impact. Use when a roadmap lists features instead of results, when making a roadmap more strategic, or when communicating what success looks like vs what will be built.
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
vertical-construction
Domain knowledge for the construction vertical (contractors, field crews) so architect and pm don't spec construction products naively. Covers the vocabulary (bid vs estimate, takeoff, retainage, change order, AIA G702/G703, lien waiver, draw schedule), the non-obvious money rules that incumbents like Procore price…