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/random6913/claude-code-superkit/output-enforcementnpx skills add RaNDoM6913/claude-code-superkit --skill output-enforcementgit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWhat 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 | $0.00044 | $0.00438 |
| Opus 5 | $0.00022 | $0.00219 |
| Sonnet 5 | $0.00009 | $0.00088 |
| Haiku 4.5 | $0.00004 | $0.00044 |
Grade A, and why
output-enforcement 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.
What it actually says
Full Output Enforcement
Never produce incomplete code. Every response must contain complete, runnable code.
Banned Patterns
These MUST NEVER appear in generated code:
// ...
// rest of code
// rest of the implementation
// implement here
// TODO: implement
// TODO
// existing code...
// previous code remains
// ... (other methods)
// similar to above
/* ... */
# ... rest
# TODO
Execution Protocol
Before Writing Code
- Scope: Count files and functions to generate
- Build: Write every file completely — no shortcuts
- Cross-check: Verify every import resolves, every type exists, every function is defined
During Writing
- Write complete file from first line to last
- If a file is too long for one response, write to a clean breakpoint (complete function/class)
- Mark pause point:
[PAUSED — 3 of 7 files complete. Continuing with AuthService.ts]
Quick Check (Run Before Every Response)
- Search for banned patterns in your response
- Verify every
importhas a matchingexport - Verify every type reference has a definition
- Verify no function calls reference undefined functions
Token Limit Handling
If approaching token limit mid-file:
- Finish the current function/class completely
- Add pause marker with progress tracking
- In next response, continue from the marker — don't repeat completed code
Format:
[PAUSED — AuthController.ts: 4 of 6 methods complete]
[Completed: login, logout, refresh, validate]
[Remaining: resetPassword, changeEmail]
The Rule
Incomplete code is worse than no code. A placeholder // TODO becomes invisible tech debt. A complete implementation can be reviewed, tested, and shipped.
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 · 70 lines · 44 tokens per session scan A 203bac4fc164
output-enforcement is a skill published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 438 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 2026-08-31.
Other skills, from other repositories
apm-review-panel
Use this skill to run a multi-persona expert advisory review on a labelled pull request in microsoft/apm. The panel fans out to five mandatory specialists plus a test-coverage specialist (active on every PR that touches src/) plus three conditional specialists (auth, doc-writer, performance-expert), all running in…
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
apm-spec-guardian
Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/.schema.json), or the conformance fixture seed…
apm-triage-panel
Use this skill to triage one microsoft/apm issue selected by the daily sweep, the status/needs-triage fast path, or manual dispatch. Emit one synthesized comment with a decision, label set, exact milestone, and suggested next action.
batch-bug-shepherd
Use this skill to drive a batch of suspected bugs in microsoft/apm from raw issue list to mergeable PR queue. Fan out one triage subagent per issue (LEGIT / UNCLEAR / FIXED-AT-HEAD), gate every legit bug against PRINCIPLES.md via an apm-ceo strategic-alignment pass, cross-reference legit issues against open PRs, then…
cli-logging-ux
Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (richsuccess, richwarning, richerror, richinfo, richecho), DiagnosticCollector, STATUSSYMBOLS, CommandLogger, or any…