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/lhh1301506137/cotend/cotend-project-initnpx skills add lhh1301506137/CoTend --skill cotend-project-initgit clone --depth 1 https://github.com/lhh1301506137/CoTendWrote 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/lhh1301506137/cotend/cotend-project-init)<a href="https://agentmods.dev/skills/lhh1301506137/cotend/cotend-project-init"><img src="https://agentmods.dev/badge/skills/lhh1301506137/cotend/cotend-project-init.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 | $0.00063 | $0.02603 |
| Opus 5 | $0.00032 | $0.01301 |
| Sonnet 5 | $0.00013 | $0.00521 |
| Haiku 4.5 | $0.00006 | $0.00260 |
Grade A, and why
cotend-project-init 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 6d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoTend Project Init
Protocol target: cotend-collaboration-v2.01
Project Init is the canonical initialization orchestrator. It routes to stable owners; it is not a second product-development, semantic-alignment, Tooling, Plan Tree, or reporting implementation.
Hard Boundaries
- Inspect before asking which project mode applies. Resolve framework impact before Auto Mode or broad reads.
- Project Init is the sole owner of
user_facing_language_resolutionduring Init. Never infer language from conversation, locale, repository text, filenames, model output, runtime profile, or identity. - Project Init must not classify, execute, load, call, delegate, or wrap
$cotend-semantic-alignmentor$cotend-diagnose-only. Do not loadcotend-collaboration/references/project-intelligence.mdduring ordinary Init. Do not use grill-me, Idea to Consensus, or Project Intelligence inside Init for product meaning. - Do not create protected L0-L2 meaning, confirmation, a parallel semantic tree, a second impact/language/reconstruction resolver, a language ledger, or an automatic canonical writer.
- A supplied
same_primary_session_handoffis point-in-time input, never current truth. It is eligible only with literal$cotend-session-handoffin the current input; never discover it after restart/reconnect/resume. - Critical, destructive, public/release, credential/private-data, scope, unresolved P0/P1, final acceptance, language conflict and integrity gates still stop for the user.
- Full and Adaptive use the same language resolver, impact selection, validator, repair budget, stop/readiness result, and outer handback.
- A standalone invocation returns control before product work. A bounded ordinary follow-on explicitly authorized in the same instruction may run only after the Init report and only when no specialized decision blocks it.
Direct Reference Router
Read a triggered direct reference completely. Do not preload all references, and do not reconstruct a missing owner from memory.
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 662 B
- references/auto-mode-and-onboarding.md 10 KB
- references/external-reviewer-sync.md 2.8 KB
- references/framework-impact-index.json 33 KB
- references/framework-maintenance/external-reviewer-sync.md 3.8 KB
- references/framework-update-routing.md 6.4 KB
- references/governance-language-pre-handback.md 8.2 KB
- references/initialization-core-workflow.md 6.1 KB
- references/language-and-runtime.md 8.4 KB
- references/maintenance-and-coordination.md 8.0 KB
- references/plan-tree-and-semantic-safety.md 4.1 KB
- references/reporting-and-handback.md 11 KB
- references/routing-and-planning.md 11 KB
- references/verification-and-closeout-workflow.md 6.8 KB
- scripts/check_cotend_governance_language.py 11 KB runs code
- scripts/maintain_project_agents_router.py 8.8 KB runs code
- scripts/resolve_framework_update.py 43 KB runs code
- scripts/validate_governance_language.py 24 KB runs code
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.
- 6d ago First seen · 213 lines · 63 tokens per session scan A 30edc6a16511
cotend-project-init is a skill published in the GitHub repository lhh1301506137/CoTend (2 stars, last pushed 14d ago), licensed Apache-2.0. It adds 63 tokens to every session and 2,603 once invoked, about $0.0003 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
agent-creator
Create and configure AiderDesk agent profiles by defining tool groups, approval rules, system prompts, subagent settings, subagent filtering, and provider/model selection. Use when setting up a new agent, creating a profile, or configuring agent tools, permissions, and subagent behavior.
doncheli-prd
Generate professional Product Requirement Documents (PRD) from multiple sources — Figma designs, briefs, user research, existing code. Includes risk analysis, RICE prioritization, Gherkin stories and launch plan. Activate when user mentions "PRD", "product requirements", "requirement document", "product spec", "figma…
doncheli-tech-panel
Convene a senior engineering expert panel to evaluate technical decisions. Activate when user mentions "tech panel", "technical discussion", "expert opinion", "architecture decision", "which technology", "should we use".
doncheli-context-health
Report the current state of the context window and recommend compression or cleanup actions. Activate when user mentions "context health", "context window", "how much context", "context full", "running out of context", "compress context".
doncheli-migrate
Plan and execute technology migrations with wave planning, breaking change detection and task generation. Activate when user mentions "migrate", "migration", "upgrade", "move from", "switch to", "Vue to React", "JS to TS", "v1 to v2".
doncheli-planning
Run weekly team planning with RFC review, WSJF prioritization and assignment by person/pair/squad with capacity calculation. Activate when user mentions "planning", "sprint", "weekly planning", "RFC", "team planning", "prioritize backlog", "WSJF".