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 Renzo-Tognella/DecisionsSearch --skill link-pr-to-memorygit clone --depth 1 https://github.com/Renzo-Tognella/DecisionsSearchWrote 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/renzo-tognella/decisionssearch/link-pr-to-memory)<a href="https://agentmods.dev/skills/renzo-tognella/decisionssearch/link-pr-to-memory"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/link-pr-to-memory/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/renzo-tognella/decisionssearch/link-pr-to-memory"><img src="https://agentmods.dev/badge/skills/renzo-tognella/decisionssearch/link-pr-to-memory.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 | $0.00086 | $0.01714 |
| Opus 5.5 | $0.00034 | $0.00686 |
| Sonnet 5.5 | $0.00017 | $0.00343 |
| Haiku 4.5 | $0.00009 | $0.00171 |
Grade A, and why
link-pr-to-memory 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Link PR to Memory
Você transforma PRMemory, BusinessRule, ArchitecturalDecision e CodePattern em contexto navegável por arestas tipadas. O PRMemory já contém a FeatureDescription rica; ela não é criada como nó separado nem recebe link artificial.
CORE RULE: Use a relação mais específica sustentada por evidência concreta. Nunca linke sem verificar os nós, sem rationale factual e sem preview/confirmação explícita.
When to activate
- Trigger phrases: "linka o PR X à regra Y", "conecta essas memórias", "cria o link entre PR e decisão"
- Contexts: passo final da decisionssearch-capture, depois que os nós existem; pós-criação de uma memória que tem PR implementador
Do NOT activate for:
- criar memórias → use create-*
- consultar o que já está linkado → use query-memory ou os blames
- conectar episódio de reasoning → related_memory_ids na criação do episódio
- criar ou linkar uma FeatureDescription separada → ela faz parte do PRMemory
Inputs
- source (required): memory_id de origem, normalmente PRMemory. Fonte: sessão|digest.
- targets (required): lista de memory_id, relação proposta e rationale. Fonte: create-* ou usuário.
- mode (optional, default: standalone): standalone | orchestrated.
Relações válidas
PRMemory → MemoryItem
Usar memory.pr.link_memory:
| Relação | Use quando |
|---|---|
| IMPLEMENTS | o diff implementa explicitamente uma BusinessRule ou ArchitecturalDecision |
| EVIDENCES | o PR fornece evidência de uma regra/AD/CodePattern, mas não é a implementação direta |
| MODIFIES | o PR altera o conteúdo ou comportamento representado pela memória existente |
Um CodePattern só pode ser alvo quando a memória já passou pelo gate de evidência explícita de reutilização/padronização. Um único uso no PR não basta.
MemoryItem → MemoryItem
Usar memory.link:
| Relação | Use quando |
|---|---|
| REFINES | a nova memória especifica/detalha outra sem invalidá-la |
| CONFLICTS_WITH | duas memórias são incompatíveis e a prevalência ainda não foi resolvida |
| DEPENDS_ON | uma memória só faz sentido dado o contexto da outra |
| EVOLVES_FROM | há evolução conceitual sem substituição/depreciação |
| RELATED_TO | associação real, quando nenhuma relação mais específica é verdadeira |
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.
- 1mo ago First seen · 140 lines · 86 tokens per session scan A 96c701c32287
link-pr-to-memory is a skill published in the GitHub repository Renzo-Tognella/DecisionsSearch (1 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 1,714 once invoked, about $0.0003 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
git-ai-search
Search and restore AI conversation context from git history.
remember
Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.
release
Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.
recall-rationale
Recall why a past change was made by locating the Claude Code transcript that produced it. Use when the user asks to "recall the rationale", "find the rationale", "look up the rationale", "why did I do X", "why did we do X", "why was this changed", or "find the transcript for this commit".
release-finalizer
Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.