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 agentmods add commands/vynazevedo/first-plan/cochangegit clone --depth 1 https://github.com/vynazevedo/first-planWrote 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/vynazevedo/first-plan/cochange)<a href="https://agentmods.dev/commands/vynazevedo/first-plan/cochange"><img src="https://agentmods.dev/badge/commands/vynazevedo/first-plan/cochange.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00974 |
| Opus 5 | $0.00017 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
cochange 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fp:cochange
Query do Co-change Graph.
Argumentos
$ARGUMENTS - path de arquivo (ex: internal/payment/charge.go).
Workflow
Passo 1 - Pre-flight
Verificar .first-plan/02-conventions/co-change.md ou .first-plan/08-meta/co-change.json existe. Se não, recomendar /fp:refresh 02-conventions.
Passo 2 - Lookup
Ler 08-meta/co-change.json, filtrar pares onde file_a == $ARGUMENTS ou file_b == $ARGUMENTS.
Se cache stale (> 14 dias), rodar inline:
git log --since="180 days ago" --name-only --pretty=format:"COMMIT:%H" --no-merges | \
awk -v target="$ARGUMENTS" '
/^COMMIT:/ { commit=$0; next }
/./ { files[NR]=$0; commit_files[commit] = commit_files[commit] " " $0 }
END {
for (c in commit_files) {
if (commit_files[c] ~ target) {
n = split(commit_files[c], arr, " ")
for (i=1; i<=n; i++) if (arr[i] != target && arr[i] != "") count[arr[i]]++
total++
}
}
for (f in count) printf "%.2f %d %s\n", count[f]/total, count[f], f
}
' | sort -rn | head -10
Passo 3 - Apresentar
=== Co-change graph para internal/payment/charge.go ===
Total commits afetando este arquivo (180 dias): 18
Top co-changers:
| Arquivo | Ratio | Commits compartilhados | Strength |
|---------|-------|------------------------|----------|
| internal/payment/invoice.go | 0.94 | 17/18 | strong |
| internal/handler/payment.go | 0.83 | 15/18 | moderate |
| internal/payment/refund.go | 0.72 | 13/18 | moderate |
| internal/payment/test_helpers.go | 0.61 | 11/18 | weak |
Cluster detectado: payment-subsystem
Outros membros: internal/payment/refund.go, internal/handler/payment.go
Implicação:
- Antes de mexer em charge.go, considerar tocar nos co-changers strong
- Se PR atual modifica apenas charge.go, alta chance de regressão em invoice.go
- Cluster payment-subsystem indica boundary de módulo - mudanças tipicamente afetam todos
Passo 4 - Sem co-changers detectados
=== Co-change graph para internal/util/format.go ===
Total commits afetando este arquivo (180 dias): 3
Sem co-changers significativos (insufficient sample size: precisa >= 5 commits).
Possíveis razões:
- Arquivo novo (criado recentemente)
- Arquivo estável (raramente mudado)
- Frozen zone (sem manutenção ativa)
Considere:
- /fp:hot para verificar se está frozen
- /fp:owner internal/util/format.go para descobrir dono
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.
- 5d ago First seen · 124 lines · 34 tokens per session scan A 09d199a32fd3
cochange is a command published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 10d ago), licensed MIT. It adds 34 tokens to every session and 974 once invoked, about $0.0002 per session on Opus 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
selfreview
Self code review before a release — four narrow reviewers over the change (or the whole repo), findings ranked, nothing edited.
gate
Run the full local gate (fmt, lint, test, build, docs, and fuzz when a parser changed) and report only what failed.
release
Prepare the next release per RELEASING.md — gate, price table, surface audit, changelog — and stop at the tag command.
matcha:review
🍵 Review gate — risk-based code review (L0-L3). Nothing ships until this passes.
matcha:audit
🍵 Stack health check — find overlaps, waste, and risks before they become problems.
matcha:why
🍵 Intent Discovery — problem, goals, success criteria, What → Why → How before touching code.