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 skills/waelmas/codeplow/kb-updatenpx skills add waelmas/codeplow --skill kb-updategit clone --depth 1 https://github.com/waelmas/codeplowWhat 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 | $0.00139 | $0.02324 |
| Opus 5 | $0.00069 | $0.01162 |
| Sonnet 5 | $0.00028 | $0.00465 |
| Haiku 4.5 | $0.00014 | $0.00232 |
Grade A, and why
kb-update scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kb-update - Refresh the KB after code changes
Keep the project KB aligned with reality as the code evolves. Review recent git activity and session context, surgically update stale KB notes, flag new concepts for documentation.
Scope distinction:
kb-update(this skill) — edits notes inside the vault (underArchitecture/andResearch/, excludingSessions/handoffs andResearch/Documentation Audit.md) so the agent's memory matches the current code.kb-audit— checks the project's user-owned markdown (README.md, ARCHITECTURE.md, etc.) and produces a stand-alone audit report.
Both enforce the same hard rule: no edit or flag without file:line evidence.
Step 0: Preflight
Follow the Preflight Check in the obsidian-kb awareness skill (${CLAUDE_PLUGIN_ROOT}/skills/obsidian-kb/SKILL.md). In short: verify command -v obsidian, verify timeout 3 obsidian vaults works, launch Obsidian if needed.
Step 1: Resolve the Project Vault
Follow the Vault Resolution Algorithm in ${CLAUDE_PLUGIN_ROOT}/skills/obsidian-kb/SKILL.md. Strict priority: user argument → path overlap → frontmatter project_path → strong name match → STOP and ask.
Capture both $VAULT_NAME and $VAULT_PATH.
Print the confirmation line on your first reply:
"Using vault
<Vault Name>at<path>(matched via<tier>). Reviewing KB notes against recent code changes."
If the user passed a focus area in $ARGUMENTS (e.g., "focus on the auth refactor"), capture it as $FOCUS — it will narrow Step 4's inventory.
If no vault exists at all
Tell the user:
"No knowledge base vault found for this project. Run
/kb-initto create one first, then return here to refresh it."
Stop.
Step 1b: Vault Access Sequence
Switch Obsidian's active vault to the resolved one so CLI operations work:
CURRENT=$(timeout 3 obsidian vault info=name 2>/dev/null)
if [[ "$CURRENT" != "$VAULT_NAME" ]]; then
ENCODED=$(printf '%s' "$VAULT_NAME" | sed 's/ /%20/g')
open "obsidian://open?vault=${ENCODED}" # macOS; xdg-open on Linux; start on Windows
sleep 3
CURRENT=$(timeout 3 obsidian vault info=name 2>/dev/null)
fi
if [[ "$CURRENT" == "$VAULT_NAME" ]]; then CLI_MODE=1; else CLI_MODE=0; fi
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.
- 2d ago First seen · 215 lines · 139 tokens per session scan A c714180c85bc
kb-update is a skill published in the GitHub repository waelmas/codeplow (8 stars, last pushed 4mo ago), licensed MIT. It adds 139 tokens to every session and 2,324 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…