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 JotJunior/cstk --skill reconcile-docsgit clone --depth 1 https://github.com/JotJunior/cstkWrote 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/reconcile-docs)<a href="https://agentmods.dev/skills/jotjunior/cstk/reconcile-docs"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/reconcile-docs/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/reconcile-docs"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/reconcile-docs.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 | $0.00171 | $0.02136 |
| Opus 5.5 | $0.00068 | $0.00854 |
| Sonnet 5.5 | $0.00034 | $0.00427 |
| Haiku 4.5 | $0.00017 | $0.00214 |
Grade A, and why
reconcile-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Reconcile Docs — documentacao segue o codigo
Compara o que a documentacao de uma feature (ativa ou arquivada) afirma com o que o
codigo faz hoje e atualiza so os trechos divergentes. E o sentido inverso da
converge (que adiciona tarefas para o codigo alcancar a spec). Jamais altera
codigo: a unica escrita possivel e em documentos da feature, sempre validada por
scripts/doc-guard.sh.
Invocacao
/reconcile-docs <feature> [--dry-run]
/reconcile-docs --all [--dry-run]
| Argumento | Regra |
|---|---|
<feature> |
nome kebab-case, com ou sem prefixo AAAA-MM-DD- |
--all |
todas as features ativas e arquivadas; exclusivo com <feature> |
--dry-run |
nenhuma escrita (inclusive reconciliation.md); acoes proposed-* |
| nenhum argumento | erro de uso: mostre a sintaxe acima e encerre sem alterar nada |
Raiz do projeto = diretorio de trabalho corrente; precisa conter docs/specs/. Sem
ela, encerre informando. Recomende --all --dry-run antes de --all.
Gravacao: so com git. Sem --dry-run, rode "$SKILL/scripts/git-probe.sh" can-write --root . ANTES de qualquer escrita; qualquer resultado diferente de WRITE<TAB>allowed
(exit != 0, denied-no-git ou script ausente) = RECUSA: execute como --dry-run
forcado e emita o aviso no-git-write-refused. Detalhes e politica completa em
references/write-policy.md.
$SKILL abaixo = diretorio desta skill (.../skills/reconcile-docs).
Fluxo por feature
- Localizar:
"$SKILL/scripts/locate-feature.sh" --root . --name <feature>(exit 3 = inexistente e 4 = ambiguo: liste os candidatos e encerre sem alterar; exit 2 = nome invalido). Homonima ativa+arquivada: reconcilie a ativa e informe a arquivada (archived-shadowed) no relatorio. - Snapshot:
"$SKILL/scripts/git-probe.sh" status --root .(base da auditoria). LinhaSTATUS no-git= sem git: a escrita e recusada (--dry-runforcado, avisono-git-write-refused); a analise segue, sem priorizacao e sem auditoria. - Ancoras:
"$SKILL/scripts/extract-anchors.sh" --root . --feature-dir <dir>(TSVkind token doc:line presence). E o unico escopo de busca no codigo. exit != 0 (inclusive documento ilegivel, exit 1) = nao verificavel: reporteunverifiablee nao trate a lista parcial como completa. - Priorizar (opcional):
"$SKILL/scripts/git-probe.sh" changed-since --root . --feature-dir <dir>. So atalho; a verificacao le SEMPRE o codigo atual. - Comparar e classificar cada ancora/afirmacao lendo o codigo (Read/Grep/Glob),
conforme
references/classification.md(5 tipos, regra MUST/MUST NOT,unverifiable, nao-copia de segredos). Releia a linha citada antes de gravar. - Escrever (so sem
--dry-rune comcan-writepermitido; verreferences/write-policy.md), para cada alteracao:doc-guard.sh check --root . --feature-dir <dir> <doc>(exit != 0, inclusive script ausente = negado, acaoignored) -> Edit so do trecho divergente -> marcador inline[reconciled:<kind> <date> evidence=<ref>](scripts/markers.sh next-fr <spec.md>numera o novo FR) ->markers.sh lint <doc>emarkers.sh verify --root . <doc>(devem passar). - Registrar: so se algum documento mudou, monte o corpo a partir de
templates/log-entry.mdnum arquivo temporario e rodereconciliation-log.sh append --feature-dir <dir> --date <hoje> --summary-file <arq>(exit 3 = vazio, nada gravado). Sem alteracao, NAO grave nada. - Auditar:
git-probe.sh statusde novo; entrada nova fora da allowlist =audit: violationno relatorio (sem git nao ha gravacao:skipped-no-git). - Relatorio na conversa conforme
templates/report.md(cada linha com evidenciaarquivo:linhaouabsent:<caminho>).
What ships with it
11 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 936 B
- references/classification.md 4.7 KB
- references/write-policy.md 3.6 KB
- scripts/doc-guard.sh 4.8 KB runs code
- scripts/extract-anchors.sh 5.9 KB runs code
- scripts/git-probe.sh 4.2 KB runs code
- scripts/locate-feature.sh 5.4 KB runs code
- scripts/markers.sh 5.7 KB runs code
- scripts/reconciliation-log.sh 3.7 KB runs code
- templates/log-entry.md 225 B
- templates/report.md 1.6 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.
- 23d ago First seen · 125 lines · 171 tokens per session scan A 42596aaac0ae
reconcile-docs is a skill published in the GitHub repository JotJunior/cstk (24 stars, last pushed 4d ago), licensed MIT. It adds 171 tokens to every session and 2,136 once invoked, about $0.0007 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
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.