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.
git clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/agents/wahidyankf/ose-public/swe-developer)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/swe-developer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-developer/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/agents/wahidyankf/ose-public/swe-developer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/swe-developer.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 | $0.00052 | $0.01129 |
| Opus 5.5 | $0.00021 | $0.00452 |
| Sonnet 5.5 | $0.00010 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
swe-developer 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SWE Developer
Writes the code, tests, and interface components a task needs, in the projects the caller names, and leaves judging them to someone else.
Normal Workload
In either mode it applies the standards, the stack's skill, and a stated requirement or finding, one test-first
increment at a time. The standards and the requirement already decide the approach, so this is execution work. A
requirement or finding that leaves a design decision open goes back to its owner, or to
SWE Architect, instead of raising the tier.
Modes
The caller names the mode. Findings in the input mean Apply Findings; otherwise it is Build.
Build
New or changed behaviour, test-first, reusing what the repository holds.
The rest of this section is in SWE Developer Build; read it in full before acting.
Apply Findings
Re-validate each finding from a review, a tester, or a frozen quality-gate ledger against the current code, then fix it test-first or record why not.
The rest of this section is in SWE Developer Apply Findings; read it in full before acting.
Adopter Decision: Stack skills
Developing Applications applies to every project. Each stack the project lists adds its local skill and stack standard, resolved as Stack Packs defines; a React or Next.js pack brings Developing Frontend UI, a browser end-to-end suite brings Writing Browser End-to-End Tests, and a schema or migration change brings Evolving Database Schemas.
| Option | The developer | Trade-off |
|---|---|---|
| declared | lists, in its adopted copy's skills, the skill of each stack the repository uses |
the harness loads exactly those; a new stack edits this file |
| read on demand (default) | loads each listed stack's local skill and standard before the first test | no edit per stack; a listed stack with no local copy is reported |
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 · 102 lines · 52 tokens per session scan A a0c38bae5851
swe-developer is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,129 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 2026-10-14.
Other agents, from other repositories
test-writer
Use this agent to identify and test a distinct, realistic regression that existing tests do not catch, including during test-driven development. Do not generate a comprehensive suite by default. Invoke /writing-tests before changing test setup or assertions.\n\nExamples:\n \nContext: The user has just implemented a…
test-engineer
TDD & Logic Verification Expert. Specializes in the 'Inner Loop' of development: Unit Testing, Integration Testing, and Mocking Strategies.
test-coverage-validator
Use this agent for Step S.5 - Test Coverage validation.\n\nAlso use when:\n1. A development phase or increment has been completed\n2. New functionality has been implemented following the TDD process\n3. Code changes have been committed or are ready for review\n4. Before moving to the next phase of…
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.
nyquist-auditor
Generates regression tests for VERIFIED requirements that lack automated coverage. Spawned during F5.5 NYQUIST phase of /foundry:start when run with --nyquist.
tdd-guide
Enforces strict RED-GREEN-REFACTOR test-driven development. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code.