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 ayberkcansever/ai-skills --skill graph-retrogit clone --depth 1 https://github.com/ayberkcansever/ai-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/ayberkcansever/ai-skills/graph-retro)<a href="https://agentmods.dev/skills/ayberkcansever/ai-skills/graph-retro"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/graph-retro/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/ayberkcansever/ai-skills/graph-retro"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/graph-retro.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 | $0.00062 | $0.02030 |
| Opus 5.5 | $0.00025 | $0.00812 |
| Sonnet 5.5 | $0.00012 | $0.00406 |
| Haiku 4.5 | $0.00006 | $0.00203 |
Grade A, and why
graph-retro 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 1mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Graph Retro
Post-deploy retrospective on the SDLC skill chain (interview-plan → write-plan → execute-plan → thermo-nuclear-code-quality-review). Optional: brainstorm before interview-plan. Reads one ticket's plan + spec artifacts, extracts every failure signal, attributes each to the skill that should have prevented it, and proposes one-line amendments.
The insight: the chain already produces its own improvement telemetry — drift notes, blockers, review findings, overridden recommendations — but nothing consumes it. This skill is the feedback edge that closes the loop.
This skill never edits skill files on its own. Output is proposals; the user approves each before anything is applied. Approved amendments are committed to the skills directory with the ticket ID in the commit message — keep that directory a git repo so every change is a reviewed, revertible commit whose history answers "why does this rule exist".
Announce at start: "I'm using the graph-retro skill to retro this ticket."
When to run
After the ticket is merged and the deploy is verified, or whenever the user
says "retro this ticket" / invokes /graph-retro. Not part of the implement
loop — do not run it as the next command after execute-plan or the review.
Also re-run on an old ticket when an escaped defect traces back to it — the
defect is an additional signal, attributed to the review skill (a review
lens gap).
Step 1 — Locate artifacts
Resolve <TICKET-ID> from the branch name or ask once. Read, in order found:
- Plan file:
docs/features/<TICKET-ID>/*-implementation-plan.md, elsedocs/plans/<TICKET-ID>/*-implementation-plan.md - Spec:
docs/features/<TICKET-ID>/design.md, elsedocs/specs/<TICKET-ID>/spec.md
Multi-repo tickets: check every repo in the workspace for the same
<TICKET-ID> paths. Missing plan AND spec → report "nothing to retro" and
stop.
Step 2 — Extract signals
Scan the artifacts for exactly these, quoting each verbatim with its location:
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.
- 1mo ago Changed · +11 lines · -31 tokens per session 21e2a73f1770
- 1mo ago Changed · +26 lines d8fd62119d53
- 1mo ago First seen · 140 lines · 93 tokens per session scan A 81ef9088295c
graph-retro is a skill published in the GitHub repository ayberkcansever/ai-skills (2 stars, last pushed 25d ago), licensed MIT. It adds 62 tokens to every session and 2,030 once invoked, about $0.0002 per session on Opus 5.5. 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
fetch-url
Fetch a single URL and print its content as Markdown. Use when you need to read a web page, documentation page, or API reference without indexing it. Accepts http(s):// and file:// URLs and writes the result to stdout.
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
accessibility
Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…