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/saigonxiii/evc/helpgit clone --depth 1 https://github.com/SaigonXIII/evcWhat 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 | $0.00000 | $0.01046 |
| Opus 5 | $0.00000 | $0.00523 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
help 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help — EVC Command Reference
Print all available commands grouped by use case. When the user runs /help, output the full index below.
Output
════════════════════════════════════════════════════
EVC — Command Reference
════════════════════════════════════════════════════
WEEKLY CADENCE
/project:monday Start the week (5-in-1 chain)
/project:friday Close the week (4-in-1 chain)
CONTENT ENGINE (daily social posts)
/project:intel-scan Weekly research — competitors, trends, algo
/project:performance-review Analyze past content with platform metrics
/project:content-plan Build weekly brief with 5-day calendar
/project:content [day] Produce one day's post + visual
/project:content-week Batch produce all 5 days
/project:crosspost Adapt content for X, LinkedIn, Threads
/project:post-today Publish + auto-reply with link
/project:reply-monitor Scan mentions, draft canon-aligned replies
BLOG ENGINE (long-form articles)
/project:blog-plan [topic] Research + outline with visual map
/project:blog-draft [slug] Write 1,200-2,000 word semantic HTML
/project:blog-qa [slug] 8-check quality pipeline
/project:blog-assets [slug] Build visual templates, export PNGs
/project:blog-publish [slug] Push to CMS + sync components
/project:sync-blogs Sync CMS data to components
/project:repurpose [slug] Fan a blog into X/LinkedIn/newsletter/quote cards
QA & REVIEW
/project:content-qa 6-check pipeline + brand voice score (0-50)
/project:content-review Audit copy against brand canon
/project:stop-slop Detect and remove AI writing patterns
/project:copy-review Brand voice + legal guardrail check
/project:site-audit Scan live site for brand drift
/project:compliance-check Jurisdiction-aware content compliance
COMMS
/project:comms-scan Unified inbox triage (Gmail + X + PM)
/project:slack-comms Read, post, summarize Slack channels
/project:community-harvest Convert community questions into content topics
PRODUCTIVITY
/project:save-session Save full session state
/project:resume-session Load last session and continue
/project:deep-research Multi-source research with cited reports
/project:lesson-capture Record what worked/failed
ONBOARDING & SETUP
/project:start First-time setup wizard
/project:setup-canon Interactive brand rules builder
/project:upgrade Pull latest + re-render templates
/project:security-audit Secret scan + permission check
/project:help This command index
GOVERNANCE & WORKFLOW (Phase 1-3 additions)
/project:canon-diff [since] View canon-rules.json change history
/project:reference-capture Screenshot live site before building visuals
/project:export-clean [file] Strip internal drawer from staging HTML
PIPELINE REFERENCE
/project:content-pipeline Full Content Engine flow diagram
/project:blog-pipeline Full Blog Engine flow diagram
STAGING
/project:stage [type] [name] Build per-asset staging HTML (blog/social/asset)
/project:dashboards Build master dashboards (commands/canon/brand)
════════════════════════════════════════════════════
PIPELINES AT A GLANCE
Content Engine (Mon-Fri):
/intel-scan → /performance-review → /content-plan → [Review]
→ /content-week → [Review] → /post-today
Blog Engine (per article):
/blog-plan → [Review] → /blog-draft → /blog-qa → [Review]
→ /blog-assets → /blog-publish
KEY FILES
brand/canon-rules.json Brand rules (banned phrases, USPs)
content-engine/config.md Audience, schedule, tone
content-engine/memory/ Persistent learning (lessons, performance)
config.env Company config (name, URL, colors)
════════════════════════════════════════════════════
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 · 101 lines · 0 tokens per session scan A 893c4fdae1b6
help is a command published in the GitHub repository SaigonXIII/evc (56 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,046 tokens. 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
review-tool
Research a tool or product for skill-gap, architecture, and verb-fit per the Anatomy framework.
setup
First-run setup — replace the fictional company and authors with yours.
content-status
Scan all content directories and report status of drafts, ideas, and published content.
draft-blog
Scaffold a blog post with proper structure, voice, and frontmatter.
review-content
Review content for brand alignment, lead placement, bio consistency, and proof points.
voice-check
Check a draft against the author's voice profile and flag deviations.