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 Snowflake-Labs/cocoplus --skill cocotracegit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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/snowflake-labs/cocoplus/cocotrace)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/cocotrace"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cocotrace/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/snowflake-labs/cocoplus/cocotrace"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cocotrace.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 | $0.00022 | $0.01956 |
| Opus 5.5 | $0.00009 | $0.00782 |
| Sonnet 5.5 | $0.00004 | $0.00391 |
| Haiku 4.5 | $0.00002 | $0.00196 |
Grade A, and why
cocotrace 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CocoTrace — Requirements-to-Implementation Traceability
Overview
CocoTrace maintains a directed dependency graph: bloom.md → discuss.md → spec.md → plan.md → build-output → eval-results. SHA-256 content hashes detect genuine changes (not timestamp drift from git operations). Staleness propagates downstream from any changed node.
Why SHA-256, not timestamps: Rebase and cherry-pick change file mtimes without changing content. SHA-256 only signals real changes.
Commands
$trace build
-
Execute the
cocotrace/trace-checkcontract (deterministic, no LLM, Tier 2 async) -
Read output
lifecycle/trace.json -
Display summary table:
Artifact Status SHA-256 ────────────── ──────── ────────── bloom.md current abc12345 discuss.md stale def67890 spec.md stale (downstream of discuss.md) plan.md missing — build-output missing — eval-results missing — -
Create git commit:
chore(cocotrace): update artifact traceability graph -
Output: "[N] current, [M] stale, [P] missing"
Idempotent: Running twice on unchanged content produces bit-identical trace.json.
$trace gaps
-
Read
lifecycle/trace.json -
Read
lifecycle/spec.md- If spec.md has no
##section headings: output "spec.md has no section structure — gap analysis requires structured sections" and exit gracefully
- If spec.md has no
-
Extract requirement sections (all
##headings in spec.md) -
Check
lifecycle/build/for corresponding implementation files -
Report:
## Traceability Gap Analysis ### Orphaned Requirements (in spec.md, no build artifact) - § 3.2 Model Selection Criteria — no matching build artifact found ### Uncovered Code (in build/, no traceable requirement) - lifecycle/build/helper-utils.sql — not referenced in spec.md ### Coverage Requirements covered: 4/6 (67%) Implementation traced: 3/4 (75%)
$trace show <artifact>
- Read
lifecycle/trace.json - Trace backward from
<artifact>: which upstream nodes inform it? - Trace forward: which downstream nodes it produces?
- Display ASCII dependency chain with YOU ARE HERE marker:
What ships with it
5 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.
- 1mo ago First seen · 180 lines · 22 tokens per session scan A 840f87bc0094
cocotrace is a skill published in the GitHub repository Snowflake-Labs/cocoplus (726 stars, last pushed 20d ago), licensed MIT. It adds 22 tokens to every session and 1,956 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
ai-agent-evaluation-benchmarking
Autonomous AI agent benchmark evaluation register: task completion rates, planning accuracy, tool invocation precision, and cost benchmarks.
critical-review
Radical-honesty architectural review — questions code, methodology, design, and operational fitness.
code-reviewer
A code-review workflow written in Chinese that checks software changes for correctness, security, performance, and maintainability. It also defines a report format for critical issues and suggestions.
test-writing
Write tests that catch real regressions — behavior-focused, minimal mocking, edge cases chosen from the code's actual branches. Use when adding tests for new code or backfilling tests for a fix.
ai-agent-evaluation-benchmarking
Autonomous AI agent benchmark evaluation register: task completion rates, planning accuracy, tool invocation precision, and cost benchmarks.
skill-steward
Use when installed skills need a lifecycle audit: scans the forge registry and the configured skill directories for staleness, overlap, and conflicting triggers, then proposes a retire, promote, merge, or quarantine action per skill with evidence.