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 commands/sjarmak/coding-agent-workflows/implement-reviewgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWhat 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 | $0.00020 | $0.01026 |
| Opus 5 | $0.00010 | $0.00513 |
| Sonnet 5 | $0.00004 | $0.00205 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
implement-review 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Implement + Self-Review
The default per-task loop. A single agent implements a change via focus, then
runs simplify and code-review as a hard verification gate before
finalizing. The gate checks that the work actually fulfills what was asked, not
just that the code is stylistically clean.
This is a runtime-neutral spec. It originated as an orchestration formula run by worker agents; the runtime-specific task-tracker and retry calls have been replaced with neutral equivalents so any orchestrator (a Claude Code session, a Codex run, an Amp thread, or a shell loop) can drive it.
Inputs
| Input | Source | Description |
|---|---|---|
task |
caller | The unit of work: a tracker ID, an issue, or a written description. |
base_ref |
caller | Base git ref for diff comparison. Default: main. |
test_command |
project | Command to verify the work. Empty = skip. |
Steps
The steps form a DAG; each lists what it depends on. An orchestrator runs them in dependency order and stops at the gate if it rejects.
1. load-context
Understand the work before touching code. Read the task's description, acceptance criteria, and any linked context. If a prior attempt was rejected, read the rejection reason and target the specific issue it called out.
Exit: you can state what "done" looks like for this task.
2. focus (needs: load-context)
Run the focus skill on the task: plan the implementation, execute the plan
step by step, verify against acceptance criteria. Follow the skill's workflow;
don't override it. If your context fills up, commit progress and hand off to a
fresh session rather than degrading.
Exit: focus has completed its plan → execute → verify cycle.
3. run-tests (needs: focus)
Run test_command. If it's empty, skip. If tests fail: read the output, fix
the implementation, commit the fix, re-run. Do not proceed until tests pass.
Exit: tests pass, or no test command is configured.
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 · 104 lines · 20 tokens per session scan A ea341a6e83e0
implement-review is a command published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,026 once invoked, about $0.0001 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 commands, from other repositories
plugin-update
Upgrade DeepInit to the latest version — pulls the newest from the marketplace (on one confirm), then guides the host-correct reload. Ends the "is my plugin stale?" dance.
check
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.
customize
Tune a DeepInit run with buttons — depth, issue detection, outputs, scope, cost, and the freshness/notification settings (disable the nudge, change its cadence/time-window) — no flags to type. Opens a native multiple-choice picker, then runs.
version
Which DeepInit version is actually running right now? Prints the LOADED version, checks it against the on-disk version, and tells you if you need to reload. No analysis.
doctor
DeepInit preflight — tools, scope, resolved config (and whether it's valid), enabled issue families, estimated cost. 0 tokens, no LLM. Offers to install the freshness hooks.
help
Show all DeepInit commands + key options, grouped and ordered by how often you'll use them. Instant, no analysis.