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 MK27MK/no-bs-skills --skill fill-the-gapsgit clone --depth 1 https://github.com/MK27MK/no-bs-skillsWrote 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/mk27mk/no-bs-skills/fill-the-gaps)<a href="https://agentmods.dev/skills/mk27mk/no-bs-skills/fill-the-gaps"><img src="https://agentmods.dev/badge/skills/mk27mk/no-bs-skills/fill-the-gaps/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/mk27mk/no-bs-skills/fill-the-gaps"><img src="https://agentmods.dev/badge/skills/mk27mk/no-bs-skills/fill-the-gaps.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 | $0.00051 | $0.00944 |
| Opus 5 | $0.00026 | $0.00472 |
| Sonnet 5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
fill-the-gaps 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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filling the gaps
The user gave you work in progress. It is incomplete, and it can be broken. This is correct. The user writes the code that says what the software must be, and you write the code that makes it run.
The tree is the specification
The user speaks to you in these forms:
| Form | Means |
|---|---|
| A signature with no body | Build this. The name and the types are the contract. |
| An empty class or module | This concept exists. Find its parts. |
| Pseudo code | The steps are correct. Write them in the language. |
| Deleted code and a comment | The old solution is dead. Do not bring it back. |
| A marker | Read the marker. |
- ALWAYS read the full diff, and then every file that the diff touches, before the first edit.
- NEVER repair the tree back to its last working state. Broken is the input, not the fault.
- NEVER add a feature that no gap asks for.
Markers
A marker starts with AI. The prefix means the line speaks to you.
-
AI TODO— the code is absent. Write it. -
AI FIXME— the code is present and wrong. Replace it. -
AI NOTE— a constraint on the work near it. It is not work by itself. -
ALWAYS delete a marker when you satisfy it.
-
NEVER act on a
TODOor aFIXMEwithout theAIprefix.
The two locks
Read both locks before the first edit. The default of each one is y.
| Lock | y says |
|---|---|
lock_definitions |
The set of definitions is closed. Add none. |
lock_names |
The names are frozen. Rename none. |
lock_definitions
- IF
lock_definitionsisy, THEN write no new function, no new class, and no new method. Put the work in the definitions that the tree already holds. - IF a call has no definition, because the user deleted it or never wrote it, THEN delete the call and each line that serves only the call. NEVER write the absent definition.
- ALWAYS do that work again with the builtin types and the builtin functions of the language, or with a library that the repository already imports.
- ALWAYS name, in your answer, each call that you deleted, and what does the work now.
- IF the work cannot run without one new definition, THEN stop. Name it, say why the builtins are not enough, and wait.
- IF
lock_definitionsisn, THEN write the definitions that the gaps ask for, and no more.
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.
- 11d ago First seen · 77 lines · 51 tokens per session scan A 5f84bdd11455
fill-the-gaps is a skill published in the GitHub repository MK27MK/no-bs-skills (2 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 944 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
debugger
Systematic debugging method: 5-step root-cause analysis (capture, isolate, hypothesize, investigate, fix & verify) plus common bug-pattern reference. Use when errors, exceptions, test failures, or unexpected behavior appear. Loaded automatically by the debugger agent.
mcp-check
Validate MCP configuration and suggest improvements. Use when MCP servers fail to load, after editing .mcp.json, or when the user runs /mcp-check.
project-health-check
Audit project health across 7 dimensions (documentation, test coverage, security, code quality, dependencies, database, build/deploy) producing a scored report with prioritized fixes. Use for periodic checkups, before releases, or when the user runs /project-health-check.
doctor
Diagnose Cladding runtime health — Claude Code hook liveness and version, CI package pinning, lifecycle governance, and sentinel-miss frequency by phase × cause × fallback. Use when hooks may be silent, CI may float across Cladding releases, scan or run results look thinner than expected, or before tuning the host…
debug
Systematic bug investigation with a five-phase framework: reproduce, narrow, diagnose, fix, verify. Supports automated regression bisect via --regression flag. Produces a structured debug report with root cause analysis, regression test, and CQ/Q self-evaluations.
ccc-systematic-debugging
Root-cause debugging via the Iron Law: no fix without confirmed root cause. Reproduce → hypothesize → verify → fix. Use when investigating bugs, test failures, or…