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/soulcodex/agentic/fix-bugnpx skills add soulcodex/agentic --skill fix-buggit clone --depth 1 https://github.com/soulcodex/agenticWhat 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 | $0.00054 | $0.00525 |
| Opus 5 | $0.00027 | $0.00262 |
| Sonnet 5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
fix-bug 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 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.
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
Fix Bug Skill
Investigate and fix the reported bug systematically.
Step 1 — Understand the Bug
Gather:
- What is the expected behavior?
- What is the actual behavior?
- How is it reproduced? (steps, input, environment)
- Is there an error message, stack trace, or failing test?
If this information is missing, ask the user before proceeding.
Step 2 — Locate the Root Cause
Read the relevant code:
- Start at the reported error location or the code path described in reproduction steps.
- Trace upward through callers to understand context.
- Trace downward through callees to understand what data flows in.
- Look for: off-by-one, null dereference, wrong conditional, missing error handling, incorrect assumption about external behavior, race condition.
State the root cause explicitly before writing any fix:
"Root cause: The
findUserfunction assumes the result is never null, but the database returns null when no row matches. The null propagates touser.emailaccess, causing the crash."
Step 3 — Write a Failing Test First (if no test exists)
Before fixing, write a test that reproduces the bug and currently fails. This proves you understand the bug and prevents regression.
Step 4 — Fix
Apply the minimal fix that addresses the root cause. Do not refactor surrounding code unless it is directly related to the bug.
Step 5 — Verify
Run the test written in Step 3 — it must now pass. Run the full test suite — no regressions introduced.
Step 6 — Summarize
Output:
## Bug Fix Summary
**Root cause**: [One sentence]
**Fix**: [What was changed and why]
**Test added**: [File and test name]
**Regression risk**: [None / Low / Medium — explain if not None]
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 · 75 lines · 54 tokens per session scan A 6cc1c42f6ddf
fix-bug is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 525 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
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
survey-design
Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).
localization-design
Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
design-debt-audit
Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).
design-impact-reporting
Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).