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/treylom/knowledge-managerWrote 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/treylom/knowledge-manager/reform)<a href="https://agentmods.dev/commands/treylom/knowledge-manager/reform"><img src="https://agentmods.dev/badge/commands/treylom/knowledge-manager/reform/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/treylom/knowledge-manager/reform"><img src="https://agentmods.dev/badge/commands/treylom/knowledge-manager/reform.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 | $0.00045 | $0.02684 |
| Opus 5.5 | $0.00018 | $0.01074 |
| Sonnet 5.5 | $0.00009 | $0.00537 |
| Haiku 4.5 | $0.00005 | $0.00268 |
Grade A, and why
reform 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 1mo 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/km:reform — 대량 변형 (plan/apply/check)
$ARGUMENTS
엔진 인용 계약: 이 커맨드는 이동·frontmatter·링크 수정 로직을 새로 구현하지 않는다.
apply② 단계는skills/km-archive-reorganization.md(이동 — Mode R)와skills/km-batch-python.md(frontmatter·links)의 기존 절차를 그대로 따른다. 여기서 하는 일은 그 절차를 순서대로 호출하고, 실행 전후로 스냅샷·감사·게이트를 배선하는 것뿐이다.
0. 문법
/km:reform <plan|apply|move|frontmatter|links|check> [경로|계획서]
- 인자 없음 =
plan(vault 전체를 대상으로 계획서만 만든다). move·frontmatter·links= 그 유형 하나만 다루는plan단축이다(예:/km:reform move→ 이동 대상만 계획서에 담는다).apply는 항상 먼저 만든plan산출물(계획서)을 인자로 받는다.VAULT_PATH는commands/search.mdPhase -1 과 동일 규칙으로 정한다(추측 ❌ —km-config.json→obsidian.json"open": true판정 → 그래도 없으면 사용자에게 1회 질문).PLUGIN_ROOT는 이 플러그인 루트(scripts/km_link_gate.py가 있는 경로)로, 밖에서 주어진다.- 아래 절의 bash 블록은
$VAULT_PATH·$PLUGIN_ROOT·(있다면)$ARGUMENTS세 값이 이미 정해져 있다고 가정한다.
1. plan (dry-run · 쓰기 = 계획서 1개뿐)
입력은 _meta/KM-DESIGN.md §G(있으면) 또는 사용자 서술이다. 이 단계는 노트·폴더를 건드리지 않는다 — vault 안에서 쓰는 파일은 계획서 1개뿐이다.
TS=$(date +%Y%m%d-%H%M%S)
SOURCE="${VAULT_PATH}/_meta/KM-DESIGN.md"
if [ -f "$SOURCE" ]; then SOURCE_DESC="$SOURCE (§G)"; else SOURCE_DESC="사용자 서술(대화 맥락) — $SOURCE 없음"; fi
PLAN="${VAULT_PATH}/_meta/REFORM-PLAN-${TS}.md"
mkdir -p "${VAULT_PATH}/_meta"
# 대상 계수(근사) — move|frontmatter|links 로 좁혀 부르면 그 유형 범위만 센다.
TARGET_COUNT=$(find "$VAULT_PATH" -name '*.md' -not -path '*/_meta/*' | wc -l | tr -d ' ')
LINK_COUNT=$(grep -rho '\[\[[^]]*\]\]' "$VAULT_PATH" --include='*.md' 2>/dev/null | wc -l | tr -d ' ')
# 헤더는 변수로 우회한다(heredoc 안 리터럴 '## ' 가 바깥 절 목차 grep 을 오염시키지 않게).
SEC_TARGET="## 대상"; SEC_LINK="## 예상 링크 영향"; SEC_ROLLBACK="## 롤백 방법"; SEC_ETA="## 소요 예측"
cat > "$PLAN" <<EOF
---
schema_version: km-reform-plan-v1
source: ${SOURCE_DESC}
created: $(date +%F)
---
# Reform Plan — ${TS}
${SEC_TARGET}
- 파일 수(근사, .md 전체 — 유형 지정 시 해당 범위만): ${TARGET_COUNT}
- 변경 유형: ${ARGUMENTS:-plan(전체)}
${SEC_LINK}
- 현재 wikilink 총량(근사): ${LINK_COUNT}
- 예상 깨짐 수: 이동 대상 파일명을 위 근사값에서 별도로 grep 해 채운다(노트·폴더는 이 단계에서 건드리지 않는다)
${SEC_ROLLBACK}
- apply 실행 전 자동 스냅샷(태그 또는 stash)을 남긴다 → \`git -C "$VAULT_PATH" reset --hard km-reform-pre-<ts>\`
${SEC_ETA}
- 범위: 파일 수 기준 대략(정확한 단일 수치 금지 — 범위로만 제시)
EOF
echo "저장: $PLAN"
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.
- 1mo ago First seen · 188 lines · 45 tokens per session scan A ef09aa98fddd
reform is a command published in the GitHub repository treylom/knowledge-manager (248 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 2,684 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 2026-09-04.
Other commands, from other repositories
rename
Rename local files from what the documents say — {date}{vendor}{ref}{ext} and other templates — with the carrel CLI (dry-run first, then apply).
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.
commit
Context-aware Git commit assistant with smart pre-commit checks.