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.
git 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/commands/jotjunior/cstk/feature-00c-resume)<a href="https://agentmods.dev/commands/jotjunior/cstk/feature-00c-resume"><img src="https://agentmods.dev/badge/commands/jotjunior/cstk/feature-00c-resume/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/commands/jotjunior/cstk/feature-00c-resume"><img src="https://agentmods.dev/badge/commands/jotjunior/cstk/feature-00c-resume.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 | $0.00054 | $0.07004 |
| Opus 5.5 | $0.00022 | $0.02802 |
| Sonnet 5.5 | $0.00011 | $0.01401 |
| Haiku 4.5 | $0.00005 | $0.00700 |
Grade A, and why
feature-00c-resume 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 today.
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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature-00c-resume
Voce vai retomar uma execucao pausada do feature-00c conforme contrato
em docs/specs/_archived/feature-00c/contracts/cli-invocation.md.
Argumentos recebidos
$ARGUMENTS
Comportamento esperado
1. Parse de argumentos
short_name = primeiro argumento posicional (OBRIGATORIO, kebab-case)
--resposta-bloqueio = string OBRIGATORIA se status = aguardando_humano
--projeto PATH = default = cwd (caso operador esteja em diretorio diferente)
--allow-target-outside-session = opcional; capturar em `_scope_allow`
(`--allow-outside` quando presente). Bypass explicito e
auditado do passo 2.bis (issues #189/#190/#191).
2. Localizar state dir
_proj=$(realpath "$PROJETO")
AGENTE_00C_STATE_DIR="$_proj/.claude/feature-00c-state/$SHORT"
export AGENTE_00C_STATE_DIR
if [ ! -d "$AGENTE_00C_STATE_DIR" ]; then
stderr "feature-00c-state nao existe para '$SHORT' em $_proj"
stderr "Verifique o short-name ou invoque /feature-00c novamente"
exit 6
fi
# 2.bis. projeto-alvo sob a raiz DESTA sessao (issues #189/#190/#191) —
# mesma guarda do pre-flight 1.bis do /feature-00c: hooks de guarda e
# servidor MCP so operam sob a raiz da sessao; retomar de outra raiz roda
# a onda SEM guarda enforced (tool_calls=0) e com toda tool MCP em
# SESSION_MISMATCH. Fail-closed ANTES do lock; bypass explicito auditado.
session-scope.sh check --projeto-alvo-path "$_proj" $_scope_allow || exit 3
# Backend-agnostico (state-db-runtime-parity, v6.3): sob backend SQLite
# NAO existe state.json — o estado transacional e state.db. Exigir
# state.json aqui recusaria, com exit 6, toda execucao iniciada apos
# `cstk state enable-sqlite`. Mesma forma ja usada em feature-00c.md.
if [ ! -f "$AGENTE_00C_STATE_DIR/state.json" ] \
&& [ ! -f "$AGENTE_00C_STATE_DIR/state.db" ]; then
stderr "estado ausente em $AGENTE_00C_STATE_DIR (nem state.json nem state.db)"
exit 6
fi
3. Fluxo TOCTOU-safe (ordem CRITICA — research.md Decision 5)
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.
- today Changed · +7 lines 2f0d7f9c2888
- 1mo ago Changed · +17 lines 9933519d83a4
- 1mo ago Changed · +41 lines 62b89002fad0
- 1mo ago First seen · 429 lines · 54 tokens per session scan A fa94cab35574
feature-00c-resume is a command published in the GitHub repository JotJunior/cstk (24 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 7,004 once invoked, about $0.0002 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 commands, from other repositories
factory-ticket
Implement exactly one already-claimed Linear ticket in the current worktree.
factory-next
Recommend and optionally run the next factory stage for this repo.
factory-report
Linear status report across configured repos — queue depth, triage backlog, ready-to-dispatch, blocked/held.
check
Run the full local quality gate — TypeScript check, build, dependency audit (prod-only), skill registry validate. Fast pre-commit / pre-suggestdeploy sweep.
registry
Refresh the skills registry — regenerate SHA-256 manifest from disk, then validate. Run after editing any file under .agents/skills/.
app-audit
Grade an existing app against the Mobify Studio House KB and Axiom standards — fan out the specialist auditors, produce a severity-ranked gap report, build a remediation backlog, then fix (safe fixes automatically, risky changes only with your approval).