Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add vynazevedo/first-plan/plugin install fpWrote 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/vynazevedo/first-plan/semantic-reuse)<a href="https://agentmods.dev/skills/vynazevedo/first-plan/semantic-reuse"><img src="https://agentmods.dev/badge/skills/vynazevedo/first-plan/semantic-reuse.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 5.1 | $0.00088 | $0.01571 |
| Opus 5 | $0.00044 | $0.00785 |
| Sonnet 5 | $0.00018 | $0.00314 |
| Haiku 4.5 | $0.00009 | $0.00157 |
Grade A, and why
first-plan-semantic-reuse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Reuse via BM25
Habilita busca por intencao em vez de busca por nome exato. Isso fecha o gap mais comum entre Claude e o codigo: nomes de simbolos divergem da forma como descrevemos intencoes.
Exemplos:
- Query: "validar email" -> encontra
validateEmailRFC,is_valid_email,EmailValidator - Query: "fetch HTTP com retry" -> encontra
httpClientWithBackoff,fetchWithRetries,RetryableClient - Query: "modal de confirmacao" -> encontra
ConfirmDialog,useConfirmModal,AlertConfirmation
Workflow
Passo 1 - Detectar engine
ENGINE=""
for c in "${CLAUDE_PLUGIN_ROOT}/engine/bin/first-plan-engine" "${HOME}/.local/bin/first-plan-engine" "$(command -v first-plan-engine 2>/dev/null)"; do
[ -x "$c" ] && ENGINE="$c" && break
done
Se ausente, oferecer first-plan-engine-bootstrap skill ou cair no fallback markdown.
Passo 2 - Garantir indice atualizado
DB=".first-plan/cache/search.db"
# Re-indexar se DB nao existe ou esta stale (>= 24h)
if [ ! -f "$DB" ] || [ $(find "$DB" -mmin +1440 | wc -l) -gt 0 ]; then
"$ENGINE" index --repo . --db-path "$DB" --output-json /tmp/idx.json
echo "indexado: $(jq -r .total_symbols /tmp/idx.json) simbolos em $(jq -r .elapsed_ms /tmp/idx.json)ms"
fi
Passo 3 - Query
"$ENGINE" search \
--db-path "$DB" \
--query "<intencao>" \
--limit 10 \
--output-json /tmp/search.json
Output JSON first-plan-search-v1:
{
"$schema": "first-plan-search-v1",
"query": "<intencao>",
"hits": [
{
"symbol": {
"name": "ValidateEmail",
"kind": "function",
"language": "go",
"path": "pkg/validation/email.go",
"line": 12,
"signature": "func ValidateEmail(s string) error",
"doc": "Valida formato RFC 5322"
},
"score": 8.42,
"matched_tokens": ["validate", "email"]
}
]
}
Passo 4 - Renderizar para usuario
Para /fp:reuse <intencao>, mostrar top 5 com:
- Nome + path:line
- Signature
- Doc resumida
- Score (ajuda o usuario calibrar relevancia)
- Matched tokens (transparencia sobre o ranking)
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.
- 8d ago First seen · 150 lines · 88 tokens per session scan A 5061d9b1071b
first-plan-semantic-reuse is a skill published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 14d ago), licensed MIT. It adds 88 tokens to every session and 1,571 once invoked, about $0.0004 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 skills, from other repositories
CodeShuX__mockhunter
Audit a live web page to find mock data, hardcoded values, LLM-fabricated metrics, and broken endpoints. Opens the URL in Playwright, clicks every interactive element, traces every visible value to its actual source (DB/API/mock/LLM/hardcoded), and produces a markdown report. Use when the user wants a reality check on…
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
ccb-self-diagnose
Diagnose CCB runtime, mounted daemon graph, tmux namespace and panes, provider context, queue/inbox/trace, replies/artifacts, config drift, and storage boundaries. Use when the user asks what is broken, which agent is stuck, whether CCB is mounted, why a reply did not arrive, or what to check first.
using-leankg
Use for ANY code search, navigation, or finding code logic - "where is X", "find logic Y", "how does Z work", impact analysis, dependencies. LeanKG is MANDATORY first.
RecallMax
Enhances AI memory capabilities with long-context support.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior — before proposing fixes.