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 skills add lhh1301506137/CoTend --skill cotend-collaborationgit 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-collaboration)<a href="https://agentmods.dev/skills/lhh1301506137/cotend/cotend-collaboration"><img src="https://agentmods.dev/badge/skills/lhh1301506137/cotend/cotend-collaboration/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/skills/lhh1301506137/cotend/cotend-collaboration"><img src="https://agentmods.dev/badge/skills/lhh1301506137/cotend/cotend-collaboration.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 | $0.00082 | $0.03603 |
| Opus 5 | $0.00041 | $0.01801 |
| Sonnet 5 | $0.00016 | $0.00721 |
| Haiku 4.5 | $0.00008 | $0.00360 |
Grade A, and why
cotend-collaboration 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 9d 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoTend Collaboration
Protocol version: cotend-collaboration-v2.01
Collaboration Kernel
CoTend exists to let a human guide product value while the Primary AI performs most professional reasoning and development. The framework supplies continuity, truth, evidence and stop boundaries; it must not replace the AI's current judgment with accumulated procedure.
Use four scoped authorities, never one global ranking:
| Domain | Authority | Result |
|---|---|---|
value_authority |
User | Final choice for project value, desired experience, protected L0-L2 meaning, scope, acceptance and release. |
fact_authority |
Current objective evidence | Code, data, runtime behavior and valid tests decide what is presently true. User or AI statements cannot overrule contradictory evidence. |
professional_authority |
Primary AI | Architecture, implementation, tools, tests and reversible L3/L4 choices inside protected outcomes and risk boundaries. Explain consequential judgment; do not offload routine expertise. |
risk_authority |
User authorization plus canonical stop constraints | The user selects allowed risk; Critical, irreversible, public, costly, secret/data and unknown-impact boundaries still stop through their owner. |
user_confirmed proves only a user-owned value, meaning or authorization. It
does not prove facts/technical superiority or authorize another domain. Resolve
by domain: evidence corrects facts, the Primary chooses bounded means, and only
affected work stops for unresolved value/risk.
The Primary continuously maintains project understanding, active design, coherence, evidence, route fitness and recoverability; it derives professional detail, challenge weak assumptions, pressure-tests future forms and propose important meaning changes. The user's role is low-frequency and high-leverage: goals, taste, constraints, corrections and final value/risk choices.
Classify collaboration at each material boundary:
autonomous_completion: facts and protected meaning are clear; complete the authorized coherent unit, verify it and maintain current truth.notify_and_continue: a material but AI-owned choice or non-blocking discovery should be explained at the next useful checkpoint without creating approval.stop_affected_and_align: an important protected meaning/value/risk conflict, unknown-impact boundary or unresolved integrity failure blocks only affected dependencies; explain the evidence, recommendation and needed decision.
What ships with it
51 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 527 B
- references/acceptance-test-harness.md 8.5 KB
- references/adaptive-development-experience.md 6.6 KB
- references/ai-uat.md 2.8 KB
- references/authority-and-triggers.md 29 KB
- references/browser-acceptance.md 1.3 KB
- references/capability-completion.md 7.7 KB
- references/closeout-pass.md 9.0 KB
- references/code-context-harness.md 9.9 KB
- references/collaboration-packet-templates.md 6.9 KB
- references/continuous-and-unattended.md 14 KB
- references/cotend-adapter.md 2.4 KB
- references/decision-log.md 12 KB
- references/delegation-maturity.md 14 KB
- references/development-experience-catalog.json 1.9 KB
- references/failure-memory.md 5.5 KB
- references/failure-pattern-catalog.json 2.7 KB
- references/failure-patterns/AFP-001.md 3.0 KB
- references/failure-patterns/AFP-002.md 2.9 KB
- references/framework-change-evaluation.md 9.6 KB
- references/framework-maintenance/framework-change-evaluation.md 9.6 KB
- references/framework-maintenance/skill-authoring-quality-gate.md 4.3 KB
- references/framework-maintenance/upstream-dependency-review.md 17 KB
- references/goal-completion.md 6.4 KB
- references/governance-carrier-lifecycle.md 14 KB
- references/governance-language-acceptance.md 5.7 KB
- references/idea-to-consensus.md 8.4 KB
- references/implementation-pass.md 8.0 KB
- references/native-agent-orchestration.md 13 KB
- references/plan-tree.md 19 KB
- references/project-intelligence.md 37 KB
- references/quality-sentinel.md 6.4 KB
- references/release-hardening.md 1.5 KB
- references/review-and-self-review.md 16 KB
- references/risk-and-approval.md 11 KB
- references/route-rebase-template.md 4.2 KB
- references/route-rebase.md 7.3 KB
- references/runtime-profiles.md 19 KB
- references/semantic-contract-templates.md 36 KB
- references/semantic-implementation-closure.md 13 KB
- references/semantic-reconciliation.md 22 KB
- references/session-handoff-template.md 13 KB
- references/skill-authoring-quality-gate.md 4.3 KB
- references/solution-adequacy.md 4.9 KB
- references/templates.md 39 KB
- references/upstream-dependency-review.md 17 KB
- references/verification-pass.md 12 KB
- scripts/development_experience.py 14 KB runs code
- scripts/failure_memory.py 12 KB runs code
- scripts/governance_history.py 44 KB runs code
- scripts/validate_understanding_artifacts.py 92 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.
- 9d ago First seen · 209 lines · 82 tokens per session scan A 0ca8d2f977eb
cotend-collaboration is a skill published in the GitHub repository lhh1301506137/CoTend (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 82 tokens to every session and 3,603 once invoked, about $0.0004 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
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
ticket-craft
Create Jira/Asana/Linear tickets optimized for Claude Code execution - AI-native ticket writing.
team-coordination
Multi-person projects - shared state, todo claiming, handoffs.
memstack-business-client-onboarding
Use this skill when the user says 'client onboarding', 'new client', 'onboard client', 'kickoff meeting', 'intake form', 'welcome email', or needs welcome sequences, questionnaires, and setup checklists for new clients. Do NOT use for contracts or invoicing.