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 agentmods add skills/seenode/seenode-agent-plugin/environmentnpx skills add seenode/seenode-agent-plugin --skill environmentgit clone --depth 1 https://github.com/seenode/seenode-agent-pluginWhat 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 | $0.00061 | $0.00774 |
| Opus 5 | $0.00030 | $0.00387 |
| Sonnet 5 | $0.00012 | $0.00155 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
environment 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Environment variables on Seenode
Semantics (critical)
- Set/delete env vars applies config to the running application and restarts instances.
- Env changes do not rebuild from git.
- Changing runtime image, build/start command, port, root directory, or branch requires
update_build_settings(redeploy), not env vars. - Secrets marked via
secret_keysare write-only — they cannot be read back. - For managed databases, prefer
link_database_to_applicationover pastingDATABASE_URL/DB_PASSWORDintoset_environment_variables.
List (preferred)
list_environment_variables(application_id=...)
Returns keys, isSecret, masked valuePreview, and unprotectedKeys (credential-like names that should be marked secret).
Reveal (cautious)
reveal_environment_variables(application_id=..., keys=["KEY"]|null)
Only for non-secret values, and only when the user explicitly needs plaintext or diagnosis is impossible without it. Treat anything revealed as exposed — recommend rotating and re-storing with secret_keys. Secret keys appear in withheldSecretKeys.
Set / update
set_environment_variables(
application_id=...,
variables={"KEY": "value", "OTHER": "..."},
secret_keys=["KEY"]
)
- Merges by key: omitted keys keep current values.
- Keys in
secret_keysmust also appear invariables. - Once secret, a key stays secret; to make it non-secret, delete and recreate (destructive for the old value).
- Never echo secret values back to the user — confirm that they were set.
Delete (destructive)
delete_environment_variables(application_id=..., keys=["KEY"])
Missing keys are reported in notFound. Deleting a secret destroys the value permanently. This is the only delete tool on the MCP surface for app config — confirm before removing production keys.
Common workflows
- Wire a managed database — use
link_database_to_application(default prefixDATABASE→DATABASE_HOST/_PORT/_USER/_PASSWORD/_NAME/_URL). Do not ask the user to paste DB passwords. Afterrotate_database_user_password, link again withoverwrite=true. - Non-DB secrets — set API keys and similar via
set_environment_variableswithsecret_keys. - Missing env after failed boot —
list_environment_variables→ compare to.env.example→ set missing keys (or re-link DB) → verify with runtime logs (get_application_logs). - Mark unprotected secrets — if
unprotectedKeyslists credential-like names, re-set those keys withsecret_keyspopulated.
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.
- yesterday First seen · 77 lines · 61 tokens per session scan A a7c5d10fe2ea
environment is a skill published in the GitHub repository seenode/seenode-agent-plugin (2 stars, last pushed 23d ago), licensed MIT. It adds 61 tokens to every session and 774 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…