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 ccoalm/ccl-skills --skill platform-release-engineeringgit clone --depth 1 https://github.com/ccoalm/ccl-skillsWrote 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/ccoalm/ccl-skills/platform-release-engineering)<a href="https://agentmods.dev/skills/ccoalm/ccl-skills/platform-release-engineering"><img src="https://agentmods.dev/badge/skills/ccoalm/ccl-skills/platform-release-engineering.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 149 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 151 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00122 | $0.08212 |
| Opus 5 | $0.00061 | $0.04106 |
| Sonnet 5 | $0.00024 | $0.01642 |
| Haiku 4.5 | $0.00012 | $0.00821 |
Grade A, and why
platform-release-engineering 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 today.
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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Platform Release Engineering
Owns lane/environment topology, build/deploy pipelines, traffic shifting (canary, blue-green, mirror), promotion gates using observability evidence, secret/dynamic-config distribution and rollback contracts.
- Code/test changes require self-checks; invoke
code-reviewautomatically before completion.
You do not own:
- What signals exist to judge a release — see
platform-observability. - How a request reaches a service or which subset of pods it lands on — see
platform-service-connectivityfor mesh, registry, and lane-routing primitives. This skill uses those primitives. - Service-internal change shape (handler-level refactor, DB migration mechanics) — language-specific service-architecture skills.
- Language-specific library/module tagging mechanics — the owning stack dev skill. A release task that tags a module in a multi-module repo using local path overrides (e.g. Go
replace) must run that stack's external-consumer-view verification (seego-microservice-dev) before the tag is pushed; this skill owns when a tag may ship and how registry publication is verified, not how the language toolchain validates package internals.
Skill Routing
- Use this skill for: designing the env/lane matrix, choosing a rollout strategy, defining a promotion gate, writing rollback procedure, designing a secret-distribution model, deciding static-vs-dynamic config split, building the image pipeline, choosing the deploy mechanism (custom control plane / GitOps / pipeline tool), designing approval/review workflow.
- Use
platform-observabilityfirst when the question is "what SLI does the gate consume?" — the gate definition lives here; the SLI lives there. - Use
platform-service-connectivityfirst when the question is purely about VirtualService weights / mesh routing — this skill invokes those changes, but the connectivity skill owns the primitives. - For the production release lifecycle — scope confirmation, merge authorization, tag/pipeline evidence, watchers, and post-release reset — route to
release-coordination; this skill must not own that coordination lifecycle. - Use
release-doc-writerfor the release document's substance and evidence discipline. - Use
references/python-package-registry-release.mdwhen publishing Python wheel/sdist artifacts to a private PyPI-compatible registry or verifying that a published package resolves from the registry without source/editable mappings. - Use
defect-diagnosisfor an active incident; come back here to land the recurring rollback gap.
What ships with it
14 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 266 B
- references/canary-and-rollout-strategy.md 9.6 KB
- references/config-center-via-etcd.md 13 KB
- references/custom-control-plane-boundary.md 15 KB
- references/deploy-cli-concrete-recipe.md 15 KB
- references/deploy-pipeline.md 11 KB
- references/env-and-lane-matrix.md 4.9 KB
- references/lane-orchestration-control-plane.md 22 KB
- references/multi-region-and-cluster.md 5.2 KB
- references/promotion-gate-and-review.md 14 KB
- references/python-package-registry-release.md 31 KB
- references/rollback-playbook.md 5.5 KB
- references/secret-and-config-management.md 20 KB
- references/version-authority-and-deprecation.md 5.1 KB
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.
- today Changed · +2 lines 207202ecaa00
- yesterday Changed · +20 tokens per session 04c107c45a2a
- 8d ago First seen · 304 lines · 102 tokens per session scan A 5e9002fe487d
platform-release-engineering is a skill published in the GitHub repository ccoalm/ccl-skills (6 stars, last pushed today), licensed Apache-2.0. It adds 122 tokens to every session and 8,212 once invoked, about $0.0006 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
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
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…