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 fzfclee/consulting-skills --skill fifteen-percent-solutionsgit clone --depth 1 https://github.com/fzfclee/consulting-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/fzfclee/consulting-skills/fifteen-percent-solutions)<a href="https://agentmods.dev/skills/fzfclee/consulting-skills/fifteen-percent-solutions"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/fifteen-percent-solutions/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/fzfclee/consulting-skills/fifteen-percent-solutions"><img src="https://agentmods.dev/badge/skills/fzfclee/consulting-skills/fifteen-percent-solutions.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 | $0.00056 | $0.00743 |
| Opus 5.5 | $0.00022 | $0.00297 |
| Sonnet 5.5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00074 |
Grade A, and why
fifteen-percent-solutions 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 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.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fifteen Percent Solutions
Use this skill to find actions the user can take now without waiting for full authority, perfect certainty, or broad alignment.
Method Notes
- A 15% solution is a small action inside the user's current control boundary.
- It should be meaningful enough to create evidence or movement, not just busy work.
- It is especially useful after diagnosis shows the full outcome depends on other people.
Required Inputs
Collect or infer these inputs before execution:
- desired outcome
- user's role, authority, relationships, and constraints
- blockers outside the user's control
- available time, access, and resources
- risk tolerance
If an input is missing, mark it as missing, state the assumption used, and add a validation action.
When Not To Use
Do not use when a high-risk action requires formal approval, legal review, compliance clearance, or irreversible commitment. Use risk-matrix, raci-matrix, or communications-plan first.
Step-by-Step Execution
| Step | Required input | How to execute | Output |
|---|---|---|---|
| State the desired movement | Outcome, current blockage. | Define what progress would look like in the next few days. | Near-term progress target. |
| Map control boundary | Role, authority, access, constraints. | Separate what the user controls, influences, and cannot control. | Control boundary map. |
| Generate small actions | Control boundary, available resources. | List actions that require no new permission or only low-risk informal alignment. | Candidate 15% actions. |
| Screen for usefulness and risk | Candidate actions, risk tolerance, stakeholder context. | Keep actions that create evidence, open a door, reduce ambiguity, or build trust. Remove symbolic busy work. | Shortlisted actions. |
| Choose first action | Shortlist, timing, expected signal. | Select 1-3 actions for the next 24-72 hours. | Immediate action plan. |
| Define evidence signal | Action, expected response, decision gate. | State what result means continue, adjust, or stop. | Validation signal. |
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 · 79 lines · 56 tokens per session scan A 7fc927f897e9
fifteen-percent-solutions is a skill published in the GitHub repository fzfclee/consulting-skills (7 stars, last pushed 27d ago), licensed Apache-2.0. It adds 56 tokens to every session and 743 once invoked, about $0.0002 per session on Opus 5.5. 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.
fifteen-percent-solutions compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fifteen-percent-solutionsfzfclee/consulting-skills | Skill | 7 | 27d ago | Apache-2.0 | A | 56 | Claude Code, Codex |
| taxue-calmtaxueseek/taxueskills | Skill | 24 | 1mo ago | none | A | 156 | Claude Code, Codex |
| taxue-careertaxueseek/taxueskills | Skill | 24 | 1mo ago | none | A | 303 | Claude Code, Codex |
| taxue-buildtaxueseek/taxueskills | Skill | 24 | 1mo ago | none | A | 128 | Claude Code, Codex |
| complainsaadshahd/moo.md | Skill | 38 | yesterday | MIT | A | 68 | Claude Code |
| smoothsaadshahd/moo.md | Skill | 38 | yesterday | MIT | A | 70 | Claude Code |
| flow-statefatihguner/foreman | Skill | 63 | 2mo ago | MIT | A | 96 | Claude Code |