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 MatrixFounder/Agentic-development --skill light-modegit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWrote 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/matrixfounder/agentic-development/light-mode)<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/light-mode"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/light-mode/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/matrixfounder/agentic-development/light-mode"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/light-mode.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 | $0.00023 | $0.00662 |
| Opus 5.5 | $0.00009 | $0.00265 |
| Sonnet 5.5 | $0.00005 | $0.00132 |
| Haiku 4.5 | $0.00002 | $0.00066 |
Grade A, and why
light-mode 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Light Mode
Tier: 2 (Load on specific trigger) Purpose: Provide streamlined instructions for trivial, low-risk tasks.
Definition of "Low Risk"
A task qualifies for Light Mode if ALL of the following are true:
- No new files created (except minor config tweaks).
- No database schema changes.
- No API contract changes (endpoints, request/response formats).
- No new dependencies added.
- No modifications to files matching:
auth*,payment*,crypto*,security*. - Estimated implementation time: < 30 minutes.
If ANY condition is false, ESCALATE to standard pipeline.
Exception — a mechanical split. A behaviour-preserving split of a script of an auxiliary
skill (TIER 2+, such as mermaid-authoring-guidelines) qualifies, although it creates files and
takes longer than 30 minutes. The Self-Improvement Mode of the system prompts names it a case
for /light. Every other condition above still holds.
Instructions by Role
For Analyst
- Mark the TASK title with
[LIGHT]tag. - Keep requirements minimal — focus on "What is broken?" and "What is the expected fix?".
- Skip detailed acceptance criteria if the fix is obvious.
For Developer
- Do not overengineer. Fix the issue directly.
- Do not refactor unrelated code.
- Run tests after every change.
- If you discover complexity (DB migration, API change), STOP and request workflow switch.
For Code Reviewer
- Focus on correctness and tests.
- Skip architectural nitpicks unless they are critical bugs.
- Perform a basic security sanity check:
- No credentials or secrets in code.
- No new dependencies without approval.
- No changes to auth/payment/crypto files.
- If security concerns arise, ESCALATE to
security-audit.
Escalation Protocol
If at any point the task complexity exceeds Light Mode scope:
- Inform the user: "This task requires standard pipeline due to [REASON]."
- Switch workflow: Call
/01-start-featureinstead. - The
[LIGHT]tag should be removed from the TASK.
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 Changed · +5 lines 68372ea0a9c4
- 1mo ago First seen · 70 lines · 23 tokens per session scan A e3e27253407c
light-mode is a skill published in the GitHub repository MatrixFounder/Agentic-development (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 23 tokens to every session and 662 once invoked, about $0.0001 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.
Other skills, from other repositories
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
systematic-debugging
Structured root-cause debugging loop — reproduce, isolate, form a hypothesis, verify the fix. Use whenever a bug, crash, test failure, or unexpected behavior is reported.
diagnose-hard-problem
Disciplined diagnosis loop for hard problems, diagnosing bugs and regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.