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 dinhtungdu/tangerine --skill tangerine-tasksgit clone --depth 1 https://github.com/dinhtungdu/tangerineWrote 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/dinhtungdu/tangerine/tangerine-tasks)<a href="https://agentmods.dev/skills/dinhtungdu/tangerine/tangerine-tasks"><img src="https://agentmods.dev/badge/skills/dinhtungdu/tangerine/tangerine-tasks/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/dinhtungdu/tangerine/tangerine-tasks"><img src="https://agentmods.dev/badge/skills/dinhtungdu/tangerine/tangerine-tasks.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 | $0.00026 | $0.04351 |
| Opus 5.5 | $0.00010 | $0.01740 |
| Sonnet 5.5 | $0.00005 | $0.00870 |
| Haiku 4.5 | $0.00003 | $0.00435 |
Grade A, and why
tangerine-tasks scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
AUTH_SESSION=$(curl -s "$API/api/auth/session") How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tangerine Agent Reference
🚨 CRITICAL — READ FIRST (applies to ALL task roles: worker, runner):
gh pr review,gh pr comment,gh pr merge— follow these rules strictly:
- Personal repos (repo owner matches
gh api user --jq .login): allowed when needed- All other repos: NEVER, unless the user has explicitly asked you to do so in this task
NEVER use bypass flags — these skip branch protections and CI:
--admin— bypasses all branch protection rules--forceon git push — overwrites remote history--no-verify— skips pre-push/pre-commit hooksIf CI is pending, use
gh pr merge --auto --squashto queue the merge for when checks pass. Do NOT bypass CI with--admin.This applies regardless of task role — workers and runners must follow these rules.
You are running inside a Tangerine task. Tangerine manages local agent processes, git worktrees, task lifecycle, and a web/API control plane.
Environment
| Variable | Meaning |
|---|---|
TANGERINE_TASK_ID |
Current task ID |
TANGERINE_AUTH_TOKEN |
Auth token for the Tangerine API (may be empty when auth is disabled) |
TANGERINE_API_BASE |
Full HTTP base URL for the API (e.g. http://localhost:6789). Use this for all API calls. |
TANGERINE_PORT |
Resolved HTTP port (default 3456; may come from config port or env) |
API base:
Use the API URL from your system prompt first. It is injected as
[TANGERINE: Task <id>. API: <url>. ...]and is always authoritative. The env varTANGERINE_API_BASEmatches it. Only fall back to port-based construction if neither is available.
API="${TANGERINE_API_BASE:-http://localhost:${TANGERINE_PORT:-3456}}"
echo "$TANGERINE_TASK_ID"
The port is configurable. Tangerine resolves it from TANGERINE_PORT, then config port, then default 3456. Agents always use HTTP for API calls — even when SSL is configured, the HTTP endpoint remains available and avoids TLS verification issues with self-signed certs.
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.
- 2mo ago First seen · 418 lines · 26 tokens per session scan A 63b2f95fdcec
tangerine-tasks is a skill published in the GitHub repository dinhtungdu/tangerine (5 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 4,351 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
tangerine-tasks compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tangerine-tasksdinhtungdu/tangerine | Skill | 5 | 5mo ago | MIT | A | 26 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |