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.
git clone --depth 1 https://github.com/XyndoX/good-bad-uglyWrote 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/commands/xyndox/good-bad-ugly/gbu-retro)<a href="https://agentmods.dev/commands/xyndox/good-bad-ugly/gbu-retro"><img src="https://agentmods.dev/badge/commands/xyndox/good-bad-ugly/gbu-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/commands/xyndox/good-bad-ugly/gbu-retro"><img src="https://agentmods.dev/badge/commands/xyndox/good-bad-ugly/gbu-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 | $0.00012 | $0.00359 |
| Opus 5 | $0.00006 | $0.00179 |
| Sonnet 5 | $0.00002 | $0.00072 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
gbu-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 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.
What it actually says
Run a good-bad-ugly retrospective on the current session. The goal is not a summary — it is to harvest anything that should change how future sessions run, and put it where future sessions will actually see it.
-
Sweep the session for scars. Incidents (data touched that shouldn't have been, money spent unexpectedly, a gate that passed while the product was broken), corrections the user had to make twice, specs that got superseded mid-flight, agents that went quiet, verification that turned out vacuous.
-
For each scar, ask: which layer failed? A brief missing a fence or a fixture rule → the prompt template needs the rule. A verification gap → the verify step needs the check. A user-facing surprise → the loop needs a communication step. If it couldn't have been prevented by better doctrine, say so — not everything is a process failure.
-
Write the durable artifact, smallest first:
- a one-line addition to an existing pitfalls/rules list beats a new section;
- a new section beats a new file;
- a new file needs to earn its keep. Update the project's own docs/memory for project-specific lessons; update this plugin's SKILL.md/docs for workflow-general ones. Real cases beat abstract rules — cite what actually happened, anonymized to its mechanism.
-
Report to the user: what was harvested, where it landed, and the one lesson most worth remembering. Skip ceremony if the session was clean — "no doctrine-worthy scars" is a valid outcome.
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 · 32 lines · 12 tokens per session scan A f3a4b71d6dd2
gbu-retro is a command published in the GitHub repository XyndoX/good-bad-ugly (1 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 359 once invoked, about $0.0001 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 commands, from other repositories
memories
View and manage learned memories.
forget
Delete specific memories.
learn
Add new learning to memory.
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
v-memory-refresh
(Re)index docs/superpowers prose into the local V-memory cache so recall is current. Incremental by file hash; runs fully offline (FTS5, pure stdlib). Optionally enable the semantic lane with a one-time bootstrap. Run it after pulling new docs, or when /v:remember looks stale.
v-remember
Recall relevant past Compound V context — prior decisions, failures, routing lessons, specs/plans — from docs/superpowers via V-memory (FTS5, plus semantic embeddings when bootstrapped). It surfaces EVIDENCE for planning and review, never an authority over routing. Use before planning a feature, before reviewing a…