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-semantic-alignmentgit 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-semantic-alignment)<a href="https://agentmods.dev/skills/lhh1301506137/cotend/cotend-semantic-alignment"><img src="https://agentmods.dev/badge/skills/lhh1301506137/cotend/cotend-semantic-alignment.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 | $0.00263 | $0.08537 |
| Opus 5 | $0.00131 | $0.04269 |
| Sonnet 5 | $0.00053 | $0.01707 |
| Haiku 4.5 | $0.00026 | $0.00854 |
Grade B, and why
cotend-semantic-alignment scanned grade B with 1 finding 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
| `semantic_change` | The user knowingly wants to change confirmed product meaning or a candidate route materially changes L0-L2. | Show before/after/route impact, confirm, supersede old meaning, propagate affected work, How it starts
The opening of the file, as written. The whole thing — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoTend Semantic Alignment
Companion version: cotend-collaboration-v2.01
Align product meaning before implementation details. Preserve one Plan Tree and its linked truth files; do not create a second semantic tree.
Before showing or writing user-facing governance prose, consume Project Init's persisted user_facing_language_resolution from STATUS.md or the mapped equivalent. When it is absent, invalid, or conflicting, delegate only Project Init's User-Facing Governance Language Resolution subsection to that sole owner, persist or return its result, and then continue or stop accordingly. Do not run full Init/Auto Mode, copy the source order here, infer from the conversation/repository/host, or create a competing record. This narrow delegation preserves the direct entry and does not give Init semantic-alignment authority. Full and Adaptive use the same language result. Packet headings below are an illustrative rendering; render them to the resolved normalized_tag without changing fields or authority semantics.
Independent Entry And Minimum Truth
Invoke this Skill directly. Do not run or require cotend-init or full cotend-project-init Auto Mode first; the sole-language-resolver delegation above is the only preparatory exception.
Read only the minimum project truth needed for the requested scope, in this order:
- the user's current request and latest explicit decisions;
- the binding active Plan Tree/task specification when current workflow evidence says CoTend governance is active;
- existing active
STATUS.md, PRD/brief,PROJECT-PLAN-TREE.md, target node/understanding docs, and relevant decision/knowledge records; - representative product behavior, code, tests, or UI needed to compare intended and actual meaning.
The presence of STATUS.md#cotend_workflow alone does not make stale task state binding. Missing Plan Tree or understanding records are not an Init prerequisite and do not block this Skill. Classify the request as new_baseline, then create or update the minimum canonical Plan Tree/understanding/decision surfaces only after the required L0-L2 confirmation. Never create a second truth tree.
What ships with it
2 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.
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 · 493 lines · 263 tokens per session scan B 97a4e46d16ac
cotend-semantic-alignment is a skill published in the GitHub repository lhh1301506137/CoTend (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 263 tokens to every session and 8,537 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
memstack-deployment-domain-ssl
Use this skill when the user says 'setup domain', 'configure DNS', 'SSL certificate', 'domain-ssl', 'custom domain', 'HTTPS setup', or needs to configure DNS records, SSL certificates, and custom domains for any hosting provider. Do NOT use for full deployment workflows.
memstack-development-refactor-planner
Use this skill when the user says 'refactor', 'refactoring plan', 'code cleanup', 'reduce duplication', 'simplify code', 'tech debt', 'god class', 'tight coupling', or needs to systematically improve existing code. Identifies targets, assesses risk, and builds incremental execution plans. Do NOT use for writing new…
memstack-product-feedback-analyzer
Use this skill when the user says 'analyze feedback', 'feedback analysis', 'what are customers asking for', or has support tickets, reviews, or survey data to categorize, score, and prioritize into actionable reports. Do NOT use for competitor analysis or market research.
memstack-seo-meta-tag-optimizer
Use this skill when the user says 'meta tags', 'title tag', 'meta description', 'optimize meta', 'SERP preview', or needs to write or optimize HTML meta tags for better search visibility and click-through rates. Do NOT use for schema markup or full site audits.