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 Bene-2020/plane-codex-mcp --skill ambient-projectgit clone --depth 1 https://github.com/Bene-2020/plane-codex-mcpWrote 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/bene-2020/plane-codex-mcp/ambient-project)<a href="https://agentmods.dev/skills/bene-2020/plane-codex-mcp/ambient-project"><img src="https://agentmods.dev/badge/skills/bene-2020/plane-codex-mcp/ambient-project.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.02050 |
| Opus 5 | $0.00023 | $0.01025 |
| Sonnet 5 | $0.00009 | $0.00410 |
| Haiku 4.5 | $0.00005 | $0.00205 |
Grade A, and why
ambient-project 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 8d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ambient project layer
This skill is a quiet project-recording workflow. Keep doing the user's main work normally.
Binding
When the injected context says this cwd has no project context, follow its onboarding phase and the visible conversation. Always apply the current user's explicit branch before fallback onboarding. An explicit long-term do-not-bind/do-not-ask-again instruction takes precedence: call mcp__ambient_project__decline_project_binding without calling mcp__ambient_project__list_projects, do not ask about binding again, and do not emit the fixed project-binding block. An explicit temporary “later/skip/this time/this round/not now” refusal is quiet only for the current session: do not call mcp__ambient_project__list_projects, do not ask again, and do not write a binding preference; the next new session may ask once again. Continuing another task without choosing is a current-session deferral only after the visible conversation has already shown an actual binding question or mcp__ambient_project__list_projects result; before that, even a normal work request is the first onboarding prompt and must call mcp__ambient_project__list_projects, show the real returned Plane projects, and ask the user to choose. Only an explicit request to restore or resume binding authorizes mcp__ambient_project__restore_project_binding; after restoring, call mcp__ambient_project__list_projects, wait for an explicit project choice, and call mcp__ambient_project__bind_project only after that choice. Do not guess from a Codex Project name, directory name, Git remote, or conversation.
During Ambient Plane binding, use only mcp__ambient_project__list_projects as the candidate source. codex_app__list_projects may still be used for an explicit Codex Projects request, but never as Plane binding evidence. Binding candidates may only come from the real return of mcp__ambient_project__list_projects in this turn. Never show or accept path, projectKind, or hostId, and never use a Codex local project name as a Plane candidate. Before an explicit user choice, do not call mcp__ambient_project__bind_project; never guess from a directory name, Codex Project, Git remote, or history.
What ships with it
1 file 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.
- 8d ago First seen · 57 lines · 46 tokens per session scan A b65f6328f3e4
ambient-project is a skill published in the GitHub repository Bene-2020/plane-codex-mcp (101 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 2,050 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
senmu-build-assurance
Produce read-only, evidence-graded POC, audit, reproduction, or disputed-cause verdicts. Not for implementation, routine review, retrospectives, or fixes.
RootCauseAnalysis
Structured incident investigation using Five Whys, Fishbone, blameless Postmortem, Fault Tree, Kepner-Tregoe, and FMEA — traces failures to systemic root causes rather than blaming humans. USE WHEN root cause, RCA, 5 whys, fishbone, postmortem, incident analysis, fault tree, why does this keep failing, blameless…
Vitals
Read-only macOS performance inspection: a deterministic CLI gathers the numbers, Interpretation.md turns them into a diagnosis instead of a data dump.
benchmark-workflow
Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
schedule
Manages recurring and one-off scheduled tasks. Session-scoped scheduling via CronCreate/CronDelete/CronList. Documents the cloud path for tasks that need to survive machine sleep or network drops.