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 jnerytech/specd --skill specd-apply-changegit clone --depth 1 https://github.com/jnerytech/specdWrote 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/jnerytech/specd/specd-apply-change)<a href="https://agentmods.dev/skills/jnerytech/specd/specd-apply-change"><img src="https://agentmods.dev/badge/skills/jnerytech/specd/specd-apply-change/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/jnerytech/specd/specd-apply-change"><img src="https://agentmods.dev/badge/skills/jnerytech/specd/specd-apply-change.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 | $0.00077 | $0.01012 |
| Opus 5.5 | $0.00031 | $0.00405 |
| Sonnet 5.5 | $0.00015 | $0.00202 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
specd-apply-change 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 12d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specd-apply-change
Terceiro passo do ciclo. Implementa até o gate fechar. Não arquiva, não
escreve no board e não promove requisito para .specd/specs/.
Antes de qualquer coisa
specd --version
Menor que requires_specd → pare.
1. Escolher a change e a task
specd status --json
Uma change aberta: use essa. Mais de uma: pergunte pela ferramenta de pergunta do host com as changes como opções. Nunca infira por data nem por ordem.
Dentro da change, as tasks estão em tasks/*.md com status na frontmatter:
pending | in_progress | done | blocked.
2. Ler o contrato
specd spec --json
Os requisitos que a task cita em req são a especificação. Os critérios de
aceite são a especificação de teste — cada um vira teste.
Nunca reconstrua o overlay lendo .specd/specs/ e os deltas soltos: a spec
que a skill leria não seria a que o gate lê, e ninguém veria a diferença.
3. Implementar
Até as âncoras declaradas no delta resolverem. A âncora é contrato, não sugestão: respeite exatamente o caminho e o símbolo declarados. Se o símbolo precisar de outro nome, atualize o delta no mesmo commit — requisito em voo é maleável e o preço é cobrado na hora.
Escreva código no idioma e no estilo do repositório em volta: mesma densidade de comentário, mesmos nomes, mesmos idiomas.
4. Atualizar a spec com o que a execução descobriu
"A spec" aqui é o delta, nunca .specd/specs/. Requisito que faltava,
âncora que devia apontar para outro símbolo, premissa que não se sustentou:
tudo entra no delta.md da change corrente.
É para isso que o delta é a superfície de escrita — o ciclo precisa de um lugar onde a realidade corrige a intenção sem contaminar a verdade realizada.
Mexeu em requisito? Confira se o req das tasks acompanha, ou coverage
reprova.
Nunca toque no propose.json. Ele é o registro do que a proposta dizia, e é
contra ele que a specd-archive-change recorta a revisão. Reescrevê-lo aqui
faria o recorte dar vazio sempre — o mecanismo inteiro viraria decoração, e a
revisão que ele sustenta passaria a informar que nada mudou justamente nas
changes em que mais coisa muda.
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.
- 12d ago First seen · 107 lines · 77 tokens per session scan A 8a084e59b2b0
specd-apply-change is a skill published in the GitHub repository jnerytech/specd (0 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,012 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 2026-10-02.
Other skills, from other repositories
skill
Plumb keeps the spec, tests, and code in sync. It intercepts every git commit via a pre-commit hook, analyzes staged changes and conversation history, and surfaces decisions for review before the commit lands.
diagnose
Turn a bug symptom into a fix with a regression test that locks it down. If the user opens vague ("there's a bug", "/diagnose"), interview them one question at a time until you have enough to attempt a reproduction; if you still cannot reproduce, say so explicitly. Then drive the work through five phases — build a…
tdd
Drives feature work and bug fixes through a tight failing-test-first loop. Trigger when implementing, fixing, or refactoring behavior in a codebase that already has tests. Skip for spikes, visual-only edits, throwaway scripts, and generated files.
verify
Verify that a spec.md's Acceptance criteria are observably covered by green tests before opening a PR. Reads the spec, finds the tests that cover each AC, runs the suite to confirm everything green, and reports gaps (uncovered AC, skipped tests, missing edge-case coverage). When gaps exist, automatically iterates with…
comet-verify
A workflow for verifying a Comet change after its coding tasks are complete. Comet is a tool that tracks structured software changes through stages.
gsd-add-tests
Generate tests for a completed phase based on UAT criteria and implementation.