Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/JotJunior/cstknpx agentmods add skills/jotjunior/cstk/convergeWrote 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/jotjunior/cstk/converge)<a href="https://agentmods.dev/skills/jotjunior/cstk/converge"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/converge/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/jotjunior/cstk/converge"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/converge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00126 | $0.09812 |
| Opus 5.5 | $0.00050 | $0.03925 |
| Sonnet 5.5 | $0.00025 | $0.01962 |
| Haiku 4.5 | $0.00013 | $0.00981 |
Grade A, and why
converge 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 — 673 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Converge — Reconciliação Spec-vs-Código
Audita se o código presente implementa de fato o que spec.md/plan.md/
tasks.md de uma feature prometeram, e se respeita as restrições MUST/
NON-NEGOTIABLE de docs/constitution.md do projeto-alvo. Classifica cada
divergência em missing/partial/contradicts/unrequested, atribui
severidade, e — quando há achado acionável — apenda uma tarefa residual por
achado numa fase de convergência nova, sempre ao final do tasks.md
(append-only).
Leitura semântica estática, não executa testes/build do projeto-alvo.
Read-only no projeto-alvo, exceto o append determinístico em tasks.md
(feito sempre via scripts/converge-tasks.sh, nunca via Edit/Write direto
sobre o arquivo).
Pre-requisitos
Obrigatorio: spec.md E tasks.md da feature auditada.
Se qualquer um dos dois estiver ausente no diretório informado, aborte
citando explicitamente qual artefato falta e o comando que o gera
(spec.md ausente → rode /specify; tasks.md ausente → rode
/create-tasks). MUST NOT inferir ou adivinhar o conteúdo do artefato
ausente (FR-017).
Opcional, mas recomendado:
plan.mdda feature — amplia o contexto arquitetural (paths adicionais em §Project Structure). Ausente não impede a execução:tasks.mdjá é fonte primária de paths concretos.docs/constitution.mddo projeto-alvo — habilita a escalada automática de severidadeCRITICALpor violação deMUST/NON-NEGOTIABLE. Ausente: essa escalada específica fica indisponível, mas os demais critérios de severidade (HIGH/MEDIUM/LOWpor tipo+prioridade) continuam se aplicando normalmente — não aborte a skill inteira só por isso.
Modos de invocação
Standalone (FR-014)
Skill(converge) com $ARGUMENTS = caminho do diretório da feature (ex.:
docs/specs/minha-feature). Completa sozinha, sem exigir execução
agente-00c/feature-00c ativa. Não escreve state.json (SC-006) — o
ConvergenceReport é apresentado como saída da conversa.
What ships with it
8 files 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.
- evals/triggers.jsonl 1.3 KB
- scripts/converge-status.sh 18 KB runs code
- scripts/converge-tasks.sh 13 KB runs code
- scripts/extract-intent.sh 9.5 KB runs code
- scripts/extract-must.sh 18 KB runs code
- scripts/path-contains.sh 9.1 KB runs code
- scripts/severity.sh 4.6 KB runs code
- templates/convergence-phase.md 3.1 KB
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 · +39 lines 6a8e9a6cb6d4
- 1mo ago First seen · 634 lines · 126 tokens per session scan A 5ee5383a1736
converge is a skill published in the GitHub repository JotJunior/cstk (24 stars, last pushed 4d ago), licensed MIT. It adds 126 tokens to every session and 9,812 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
Systematic debugging
Use when you hit a bug, test failure, or unexpected behavior — find the root cause before changing code.
Test-first
Use before implementing a feature or bugfix — write the failing test before the code.
Verify before done
Use before claiming work is complete — prove it with commands, do not assume.
defect-hunting
Use when reviewing code, auditing an app, writing a guard rule or test, or certifying any threshold/constant/formula. Finds the defects a diff review structurally cannot see — the second write path, the mis-calibrated constant, the rule that cannot fail. Triggers from code-reviewer, /app-audit, qa-engineer…
accessibility-gate
Use as a pass/fail gate on any diff with a user-facing surface — by code-reviewer during review, by qa-engineer during the test pass, and by any IC before claiming a UI ticket done. This is the gate the plan called for instead of an accessibility specialist role. Triggers whenever a screen, component or state changes.