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 mkslge/piazza-mcp --skill change-walkthroughgit clone --depth 1 https://github.com/mkslge/piazza-mcpWrote 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/mkslge/piazza-mcp/change-walkthrough)<a href="https://agentmods.dev/skills/mkslge/piazza-mcp/change-walkthrough"><img src="https://agentmods.dev/badge/skills/mkslge/piazza-mcp/change-walkthrough/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/mkslge/piazza-mcp/change-walkthrough"><img src="https://agentmods.dev/badge/skills/mkslge/piazza-mcp/change-walkthrough.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 | $0.00079 | $0.01782 |
| Opus 5 | $0.00039 | $0.00891 |
| Sonnet 5 | $0.00016 | $0.00356 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
change-walkthrough 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 10d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Walkthrough
Teach the change as a coherent system, then guide the user through reviewing the actual code in the order that builds understanding fastest. Explain intent, relationships, and design decisions rather than narrating the diff line by line.
Ground the Explanation
Before explaining, inspect the original request, repository instructions, plan or acceptance criteria, and the complete change in scope. Read enough surrounding code to understand existing contracts and call paths.
- Prefer a user-specified diff or comparison base. Otherwise state exactly which working-tree changes, commits, or files were reviewed.
- Include relevant untracked files; a diff alone may omit them.
- Separate behavior-changing code from tests, configuration, generated files, formatting, and incidental edits.
- Verify claims against the final code. Do not describe an abandoned plan as if it were implemented.
- Do not modify code while producing the walkthrough unless the user separately asks for changes.
If the scope or baseline remains uncertain, explain the useful verified portion and label the limitation instead of silently guessing.
Build the Mental Model First
Begin with the user's goal and the resulting behavior. In a few sentences, explain:
- What was possible before.
- What is possible now.
- Where the main responsibility lives.
- Which important behavior intentionally did not change.
Use a compact before-and-after table when it clarifies a changed contract, responsibility, data shape, or control flow. Avoid listing every file here; the ordered review tour handles implementation detail.
Show the Flow with Mermaid
For every non-trivial walkthrough, include at least one Mermaid diagram that captures the most important verified relationship. Choose the diagram from the system's actual shape:
flowchartfor control flow, data movement, dependencies, or component boundaries.sequenceDiagramfor interactions whose ordering, request/response behavior, or failure propagation matters.stateDiagram-v2for lifecycles, retries, status changes, or other stateful behavior.
What ships with it
1 file 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.
- 10d ago First seen · 199 lines · 79 tokens per session scan A ed7e5b607461
change-walkthrough is a skill published in the GitHub repository mkslge/piazza-mcp (2 stars, last pushed 17d ago), licensed MIT. It adds 79 tokens to every session and 1,782 once invoked, about $0.0004 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…