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 martineserios/thebrana --skill retrospectivegit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/retrospective)<a href="https://agentmods.dev/skills/martineserios/thebrana/retrospective"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/retrospective/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/martineserios/thebrana/retrospective"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/retrospective.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 | $0.00034 | $0.02617 |
| Opus 5 | $0.00017 | $0.01308 |
| Sonnet 5 | $0.00007 | $0.00523 |
| Haiku 4.5 | $0.00003 | $0.00262 |
Grade D, and why
retrospective scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Draft rule — review, adjust, then place in system/rules/{name}.md --> Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
count=$(grep -c "^## " ~/.claude/memory/knowledge-staging.md 2>/dev/null || echo 0) How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrospective
Store a learning in the memory taxonomy. Classifies the input by type, then routes to the canonical destination. No ruflo dependency — flat files are primary.
Spec: memory-taxonomy-ddd.md memory-taxonomy-sdd.md
ToolSearch("select:mcp__ruflo__memory_search")
Step 1 — Collect the learning
If $ARGUMENTS is non-empty, use it as the learning text. Otherwise ask:
"What did you learn? Describe the situation and the finding."
Step 2 — Classify
Apply the decision tree in order. Stop at first match.
1. Is this ephemeral — only useful for resuming this session?
→ Session state (skip retrospective; write via session-end hook)
2. Does this say "always X" or "never Y" with no context needed to apply it?
→ Rule
3. Is this a why-we-chose-X architectural or strategic choice with explicit tradeoffs?
→ Decision
4. Is this a pointer to where something lives in an external or cross-project system?
→ Reference
5. Is this a reusable solution to a recurring problem shape?
→ Pattern
6. Everything else — domain understanding, research finding, conceptual model
→ Knowledge
Set type, destination, and gate (auto | human) from the table:
| Type | Destination | Gate |
|---|---|---|
| Rule | system/rules/ — draft only, human places |
human |
| Decision | docs/architecture/decisions/ADR-NNN-*.md — stub, human commits |
human |
| Reference | ~/.claude/memory/portfolio.md |
auto |
| Pattern | ~/.claude/projects/{project}/memory/pattern_{slug}_{date}.md |
auto (after transferability filter) |
| Knowledge | ~/.claude/memory/knowledge-staging.md |
auto |
| Session | native memory dir — skip, handled by session-end | auto |
Tie-breaking: If two types are plausible, prefer lower-gate type (Pattern over Rule). Note the ambiguity in the draft so the user can override.
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.
- 7d ago First seen · 320 lines · 34 tokens per session scan D 2092766e34c2
retrospective is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed 2d ago), licensed MIT. It adds 34 tokens to every session and 2,617 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (hidden instructions, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.
continuous-learning
Use when a mistake, correction, or surprise taught the workspace something that must stick — a retro or postmortem, the same agent error corrected twice, a resolved bug's root cause, scattered notes-to-self — and route that lesson to the durable surface that fires next time. NOT a forward choice with alternatives…
context-doctor
Reduces token waste in Claude Code sessions across two axes — context footprint (auto-generates .claudeignore, guides over-read files and /clear timing) and command output (routes to a command-output proxy/hook such as rtk to trim verbose CLI stdout). In hub environments, regularly audits bloated…
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems.
salience-splitter
Splits an over-loaded always-loaded context asset (SKILL.md, CLAUDE.md, memory index) into a lean resident layer plus an on-demand layer, by when content is needed rather than by length, linked by imperative pointers. Alias: skill-splitter. Triggers: "SKILL.md too large", "split this skill", "skill is bloated", "skill…
memory-curator
Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store. Triggers on "curate memories", "clean up memories", "memory sweep".