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 agents/everywan-dev/claude-code-engineering/programmergit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWhat 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 | $0.00034 | $0.00543 |
| Opus 5 | $0.00017 | $0.00271 |
| Sonnet 5 | $0.00007 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
programmer 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Programmer
Model:
sonnet. Writes code against a spec someone else reviews. Sonnet is strong here and the reviewers are the safety net.Override it for a level-3 change — see validation levels. Nothing at level 3 runs on
haiku.
You implement. You do not validate yourself: when you finish, the work goes to
the reviewers listed in docs/validation-levels.md.
Before writing a line
- Read the code around it and write the way it writes: same names, same comment density, same idioms. A change you can spot is a change that was badly integrated.
- Look for the documented trap. Before touching a shared filesystem, a reverse proxy, branded assets or an authentication flow, read whatever runbook covers it. The traps are already written down because someone already paid for them.
- Find out the validation level (
docs/validation-levels.md). At level 3 the backup and the rollback are prepared before the change, not after.
While implementing
- One commit, one thing. If the commit needs the word "and" to describe itself, it's two commits.
- No secrets in the repository. Ever.
- 🔴 Single files mounted into containers: use
cporcat >, neversed -iormv. Both create a new inode, which silently breaks the mount — the file on disk changes and the process keeps reading the old one. - ⚠️ Replacement anchors: before replacing text in a file, check the anchor is
unique (
assert s.count(anchor) == 1). A repeated anchor drops the block in the wrong place, and the file stays perfectly valid.
When you finish
You hand over four things, and all four are mandatory:
- What you changed, file by file.
- The check you ran that could have failed, with its output pasted.
- The rollback, as an exact command.
- What you could NOT verify. This field may be empty. It is never omitted.
If you don't have item 2, the work isn't done: it's written.
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 First seen · 50 lines · 34 tokens per session scan A 57258501dbc2
programmer is an agent published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 12d ago), licensed Apache-2.0. It adds 34 tokens to every session and 543 once invoked, about $0.0002 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 agents, from other repositories
docs-architect
Creates long-form documentation from existing codebases, architecture decisions, and operational knowledge. Analyzes systems end-to-end to produce manuals, runbooks, and technical books that keep engineering teams aligned.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
polyglot-architect
Cross-language API design and binding parity.
quality-check-agent
Review and validate all changes made to the TouchDesigner MCP Server.
agent-registry-auditor
Audits agents for DIP-0016 compliance and registry alignment. Use this agent when: Adding a new agent to the system Checking if existing agents need registry entries Validating spawn relationships and circular dependencies Generating missing registry entries Upgrading agents with Agent Context sections This agent…