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/egsok/plan-tango/settingsnpx skills add egsok/plan-tango --skill settingsgit clone --depth 1 https://github.com/egsok/plan-tangoWhat 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 | $0.00084 | $0.04103 |
| Opus 5 | $0.00042 | $0.02051 |
| Sonnet 5 | $0.00017 | $0.00821 |
| Haiku 4.5 | $0.00008 | $0.00410 |
Grade B, and why
settings scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. `service_tier` — options: `Standard (default)` (description: `Normal Codex queue. No extra cost.`), `Fast (priority tier, ~1.5× speed)` (description: `Codex priority processing. Costs more. Same as --fast flag. Requir How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 1 — Read current state (resilient to broken existing config)
Run via Bash (paths quoted for spaces):
node "${CLAUDE_PLUGIN_ROOT}/skills/tango/scripts/load-config.mjs" --merge --cli '{}'
Three outcomes, each handled explicitly:
-
Exit 0 +
{merged, sources}— happy path. Parse stdout.sources[k] === "user_config"means existingconfig.jsonset this key;"default"means built-in fallback. Usemergedas "current state" for question descriptions. -
Exit 2 with a recoverable user-config error — existing
~/.claude/plan-tango/config.jsonis malformed but the wizard exists precisely to fix it. Recovery conditions (verified against the loader):Recovery condition Loader error code Source field check Always recover config_invalid_jsonn/a Always recover config_invalid_shapen/a Always recover config_unknown_keyn/a (loader emits this only for user_config) Recover only if from user-config invalid_valuerequire source === "user_config"in error payloadRecover only if from user-config invalid_typerequire source === "user_config"in error payloadThe
sourcecheck oninvalid_value/invalid_typeis required because those same codes are also emitted for bad CLI input (which would be a wizard bug, not a recoverable user-config problem).Recovery flow:
- Print warning:
"⚠ Existing ~/.claude/plan-tango/config.json is invalid: <error.detail> (field=<error.field>). Wizard will use built-in defaults as current state and write a fresh replacement (the broken file is preserved on disk until Step 6 atomic rename overwrites it)." - Set
mergedto built-in defaults:{model:null, effort:"high", max_iter:6, thread_mode:"continue", final_check:"never", lenient:false, service_tier:null, codex_profile:null, extra_codex_config:[], quiet:false, severity_aware:true, verbose_report:false, update_check:true}. Set allsources[k] = "default". extra_codex_configrecovery: attempt to read & parse the brokenconfig.jsonas raw JSON via Read tool +JSON.parse. If it parses to an array of"key=value"strings → preserve. If parse fails OR field is absent OR items don't matchkey=valueshape → use[]and warn separately:"⚠ Could not preserve extra_codex_config from broken config — falling back to []. If you had custom -c keys, re-add them after the wizard finishes."- Continue to Step 2. Step 6's atomic rename overwrites the broken file with the validated candidate.
- Print warning:
-
Exit 2 with any other error — abort wizard with the loader's
{error, detail}. This bucket includesconfig_read_failed,cli_*codes (wizard bug),missing_mode/missing_cli(wizard bug), anything else not enumerated above. Don't attempt recovery.
File-existence flag (independent of loader behavior):
test -f ~/.claude/plan-tango/config.json && echo "exists" || echo "fresh"
Save flag config_exists for Step 4 (diff-or-create branch).
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.
- 2d ago First seen · 205 lines · 84 tokens per session scan B 76e73eb45fd0
settings is a skill published in the GitHub repository egsok/plan-tango (28 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 4,103 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…