Tracely is a CI/CD system for AI agents that turns failed production traces into replayable regression tests. Development teams use it to detect and group agent failures, run the resulting cases on pull requests, and block changes that reproduce those failures. The catalogue entries provide skills for operating this trace-based testing and observability workflow.
Borrowing it
Nothing to install: this file belongs to Jwuthri/Tracely-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jwuthri/Tracely-ai/master/.claude/skills/simple-issue-description/SKILL.mdgit clone --depth 1 https://github.com/Jwuthri/Tracely-aiWrote 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/jwuthri/tracely-ai/simple-issue-description)<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/simple-issue-description"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/simple-issue-description.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.00957 |
| Opus 5 | $0.00037 | $0.00478 |
| Sonnet 5 | $0.00015 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
simple-issue-description 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 6d 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.
This is a copy
100% identical to simple-issue-description — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simple Issue Description
Write an issue a maintainer can understand in under a minute. Focus on what someone experiences and what should happen instead.
Workflow
- Read the supplied notes, conversation, issue, PR description, or diff. In a PR, also check for spec, design doc, or README changes — they often state the intent better than the description does.
- Identify the concrete problem. State who or what is affected when the source makes that clear.
- Describe the desired behavior without prescribing an implementation.
- Keep only context that helps someone understand or reproduce the problem.
- If the source is a PR or diff, describe the problem the change tries to solve, not the files or code it changes.
- Draft the issue immediately unless the problem and desired behavior cannot be determined. In that case, ask one short clarifying question.
One issue per problem. If the source bundles unrelated problems, draft the issue for the most significant one, list the others in a line each, and tell the contributor to split them into separate issues and separate pull requests.
If the source adds a capability instead of fixing a misbehavior, do not stage the absence as a bug. Describe what a user cannot do today and the full user experience of the feature: who uses it, from where, and what they see.
Do not invent user impact, reproduction steps, or certainty that the source does not support. If the source only shows cleanup, refactoring, or a possible code smell, say that no concrete problem is clear instead of manufacturing an issue — this rule wins over step 6. Reply with two or three sentences: what the source shows, and what evidence would make it issue-worthy.
If the source fixes a security weakness that is not already public, do not draft a public issue describing it. Suggest reporting it privately to the maintainer instead.
Writing rules
- Use plain language and short sentences.
- Keep the issue under 200 words unless it is clear that more is necessary to describe the reproduction steps or a large feature.
- Lead with behavior, not code, architecture, or the proposed fix. A one-sentence plain-language cause is fine when the symptom cannot be understood without it.
- Keep technical details only when they are necessary to reproduce or understand the problem. Limits and defaults that make the symptom make sense (batch sizes, quotas, caps) count as necessary.
- Preserve useful evidence such as error messages, screenshots, links, and documentation references.
- Do not mention that AI wrote or reviewed the issue.
- Avoid filler, praise, roadmap language, and exhaustive edge cases.
- Use the contributor's level of certainty. Do not present a guess as a confirmed bug; write "can" or "appears to" when the source describes a risk rather than an observed failure.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 81 lines · 75 tokens per session scan A ab3fbcbe6b76
simple-issue-description is a skill published in the GitHub repository Jwuthri/Tracely-ai (1,193 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 957 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to simple-issue-description, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
report-repair
Repair invalid local report.json files by inserting required report fields.
local-validator
Validate a local report.json file with a deterministic check-only script and no network access.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
github-ci-fix
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.