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/ghostlygawd/codeweb/pitchgit clone --depth 1 https://github.com/GhostlyGawd/codewebWhat 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 | $0.00045 | $0.00567 |
| Opus 5 | $0.00023 | $0.00283 |
| Sonnet 5 | $0.00009 | $0.00113 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
codeweb-pitch 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 yesterday.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/codeweb-pitch
Draft the business case users assemble by hand today (AI-IDEAS.md Idea 4): a one-page memo for "fund this refactor" (team lead) or "here's what codeweb found in our repo" (the shareable story). You select and narrate; the numbers come only from artifacts.
Hard rules
- Every number carries a citation to the artifact path it came from
(
optimize.md,campaign --json,.codeweb/history.jsonl,stats.json,trendoutput). A number you cannot cite does not go in the memo. - Draft only — the user reviews before anything leaves the machine. Never post, send, or
commit the memo anywhere yourself. End with: "Review before sharing — numbers are only as
fresh as the map (
mapped <date>in the report masthead)." - The honest-null voice. Blocked-tier items are stated as blocked with the gate's reason; no rounding up, no projections presented as measurements (the repo's claims-check culture).
Inputs to read (all local, all already generated)
optimize.md/codeweb_campaign— ready/blocked/review counts, LOC reclaimable, per-step gate verdicts..codeweb/history.jsonl(ornode scripts/trend.mjs --history …) — the trajectory: confirmed dups and coupling over the last N maps.node scripts/hotspots.mjs <graph>— where the risk concentrates (auditable components).stats.json(npm run stats) — the local receipt: regressions flagged before landing, cards delivered, queries served.
Shape (one page, in this order)
trajectory (one sentence + the history series) → the ask (which ready merges, expected −LOC and
cycles, per optimize.md) → what's deliberately NOT proposed (blocked tier + why) → the safety
story (every merge pre-flighted by codeweb_simulate, landed behind the diff gate) → receipts
(stats.json lifetime line).
Usage
/codeweb-pitch # draft the memo for the current map
/codeweb-pitch --audience lead # "fund this refactor" framing
/codeweb-pitch --audience share # "what codeweb found" framing for a post/README
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.
- yesterday First seen · 47 lines · 45 tokens per session scan A 1c73ca6f8a87
codeweb-pitch is a command published in the GitHub repository GhostlyGawd/codeweb (0 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 567 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 2026-08-31.
Other commands, from other repositories
map
Generate MAP.md — a relational map of every file, function, signature, and call in the repo.
sanity
Cross-check a dekko callers/uses result against a targeted grep before trusting a low/zero count.
doctor
Diagnose dekko environment/install issues (PATH shadowing, map freshness, MCP registration, plugin, hooks, CLAUDE.md policy block).
review
Review the implementation of the plan.
compliance
이전 보안 진단 보고서의 Finding들이 패치되었는지 확인하고, 변경된 코드에서 신규 취약점을 탐색합니다.
va
Vulnerability Assessment — 8차원 아키텍처 진단 + Self-Verify + Evidence Verification.