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-toolinggit 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-tooling)<a href="https://agentmods.dev/skills/lhh1301506137/cotend/cotend-tooling"><img src="https://agentmods.dev/badge/skills/lhh1301506137/cotend/cotend-tooling/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-tooling"><img src="https://agentmods.dev/badge/skills/lhh1301506137/cotend/cotend-tooling.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 | $0.00131 | $0.00987 |
| Opus 5.5 | $0.00052 | $0.00395 |
| Sonnet 5.5 | $0.00026 | $0.00197 |
| Haiku 4.5 | $0.00013 | $0.00099 |
Grade A, and why
cotend-tooling 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoTend Tooling
Companion version: cotend-collaboration-v2.01
Use evidence-backed reuse without turning a candidate into installation or
product authority. Prefer call -> compose -> adapt -> build when fit supports
it, and keep defer and reject available.
Required Procedure
- Select exactly one mode:
inventory | intake | evaluate | find | adopt | refresh | retire. If the request mixes modes, complete one result and name the next mode; do not load multiple mode bodies speculatively. - Read references/workflow.md. It owns the compact shared evidence, authority, lifecycle, parity and output contract.
- Read exactly the selected mode reference:
| Mode | Required mode reference | Additional deterministic surface |
|---|---|---|
inventory |
references/inventory-mode.md | scripts/project_inventory.py and the named checkpoint only |
intake |
references/intake-mode.md | references/catalog-schema.md |
evaluate |
references/evaluate-mode.md | catalog schema/helper only when a catalog record is touched |
find |
references/find-mode.md | catalog schema plus scripts/capability_catalog.py |
adopt |
references/adopt-mode.md | selected authority/project evidence only |
refresh |
references/refresh-mode.md | named locator/receipt; selector only after material fit delta |
retire |
references/retire-mode.md | named active receipt/dependents only |
- Validate/query metadata before detailed reads. Select at most three relevant
records, then read only their direct
source_pointerandresearch_pointers. A zero-result search is valid. - Report evidence level, independent lifecycle states, project fit, route, authority stops, rollback, actual changes and validation.
What ships with it
13 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 460 B
- references/adopt-mode.md 2.0 KB
- references/capability-catalog.json 8.7 KB
- references/catalog-schema.md 5.3 KB
- references/evaluate-mode.md 1.1 KB
- references/find-mode.md 946 B
- references/intake-mode.md 840 B
- references/inventory-mode.md 3.1 KB
- references/refresh-mode.md 1.6 KB
- references/retire-mode.md 752 B
- references/workflow.md 3.9 KB
- scripts/capability_catalog.py 33 KB runs code
- scripts/project_inventory.py 21 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.
- 1mo ago First seen · 81 lines · 131 tokens per session scan A a6df1ecc176f
cotend-tooling is a skill published in the GitHub repository lhh1301506137/CoTend (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 131 tokens to every session and 987 once invoked, about $0.0005 per session on Opus 5.5. 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
extension-creator
Create AiderDesk extensions by setting up extension files, defining metadata, implementing Extension interface methods, and updating documentation. Use when building a new extension, creating extension commands, tools, or event handlers.
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.
writing-tests
Write unit tests, component tests, and integration tests for AiderDesk using Vitest and React Testing Library. Use when creating new tests, adding test coverage, configuring mocks, setting up test files, or debugging failing tests.
deep-review
Comprehensive code review — architecture + correctness. Scope with args — diff (default), branch, all, path, or IDE selection. Delegates to reviewer agent for large scope.
review
Review code changes for bugs, security, edge cases. Scope with args — diff (default), branch, commit, path, or IDE selection. Delegates to reviewer agent for large scope.
align-context
Update all context files (task, spec, task-context, worklog) to reflect current state of work — fixes stale entries, fills missing knowledge, reports what changed.