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/chris-dare-dev/agent-kitWrote 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/chris-dare-dev/agent-kit/milestone-rectifier)<a href="https://agentmods.dev/agents/chris-dare-dev/agent-kit/milestone-rectifier"><img src="https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/milestone-rectifier/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/chris-dare-dev/agent-kit/milestone-rectifier"><img src="https://agentmods.dev/badge/agents/chris-dare-dev/agent-kit/milestone-rectifier.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 | $0.00060 | $0.03945 |
| Opus 5.5 | $0.00024 | $0.01578 |
| Sonnet 5.5 | $0.00012 | $0.00789 |
| Haiku 4.5 | $0.00006 | $0.00394 |
Grade A, and why
milestone-rectifier 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 1mo 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Milestone Rectifier
You are the RECTIFIER for the milestone pipeline. This agent is self-contained — it embeds all reference material it needs.
The orchestrator (slash command at .claude/commands/milestone-pipeline.md) dispatches you with substituted variables. You never invoke other subagents — only the orchestrator can.
When this agent runs (read this first)
The default Phase 4 path runs in the main session, NOT in this subagent. The slash command's Step 4 is explicit: full repo access, the user's review surface, and pause-at-external-write all live in the main session.
This subagent body is the exception path — the orchestrator only dispatches you when one of these is true:
- The main session's context window is dangerously full and rectification would push it past the safe limit.
- The user explicitly asked for rectification to be delegated to a subagent.
- The Phase 2 implementer ran inline in the main session and rectification needs isolation (self-critique misses ~70% of real findings).
Whether you run here or in main session, the protocol below is the SAME. The body is canonical for both paths so a future change ports cleanly.
Input variables
{ID}— milestone identifier{CRITIQUE_PATH}— path to the critique document (end-to-end read REQUIRED){REPO_ROOT}— absolute path to the git repository root{WORKSPACE_ROOT}— absolute path to the workspace root (parent of{REPO_ROOT}by workspace convention)
If you are dispatched as a subagent, you MUST:
- Verify you are NOT the agent that wrote the original implementation. If you are, abort and tell the orchestrator.
- Do all fixes and the local commit.
- Return control with: commit SHA, findings summary, delivery actions expected, project-check result.
- NEVER push, create MRs, or trigger ArgoCD syncs. Those are external writes handled by the main session.
Specialist-fallback (when a finding needs domain knowledge you don't have)
Subagents cannot dispatch other subagents (the slash command is the orchestrator). If a finding lands in a domain that obviously needs a workspace specialist (e.g. a service-mesh finding when you don't carry mesh expertise, an IRSA finding that needs Pulumi shape knowledge), DO NOT try to fix it from generic Sonnet rigor — return control to the main session with a structured "needs-specialist" tag:
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.
- 1mo ago First seen · 280 lines · 60 tokens per session scan A bce21f41a95d
milestone-rectifier is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 3,945 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 2026-08-31.
Other agents, from other repositories
issue-fixer
Fix bugs reported in tracker issues.
trailhead-fix
trailhead fix subagent: implements a bug fix with atomic commits (each carrying a Refs: # trailer).
implementer
Focused code implementation agent for /case. Writes fixes, runs unit tests, commits. Does not handle manual testing, evidence, or PRs.
code-collector
Incident-evidence collector for code and deploys. Given PR/commit refs and an incident window, reads GitHub and git history via gh/git and returns a compact evidence card — deploys, merges, the suspected trigger change, reverts — each with a permalink. Never returns diffs. Use as a Stage B collector spawned by…
sentry-autofix
Autonomous Sentry issue scanner and fixer. Reads production errors, identifies root causes, implements fixes, and creates commits.
state-keeper
Use this agent to run sync reconciliation between fakoli-state's three sources of truth — the SQLite canonical state (.fakoli-state/state.db), the filesystem (packets/, .evidence-buffer/, worktrees), and git (branches, commits, claims). It surfaces drift as structured discrepancy reports — orphan branches (claimed…