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/viitorohit/sitrepWrote 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/commands/viitorohit/sitrep/selfheal)<a href="https://agentmods.dev/commands/viitorohit/sitrep/selfheal"><img src="https://agentmods.dev/badge/commands/viitorohit/sitrep/selfheal/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/commands/viitorohit/sitrep/selfheal"><img src="https://agentmods.dev/badge/commands/viitorohit/sitrep/selfheal.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 | $0.00000 | $0.00523 |
| Opus 5.5 | $0.00000 | $0.00209 |
| Sonnet 5.5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
selfheal 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Selfheal — Health Check & Auto-Fix
Intentional (manually invoked). This command owns all file-repair behavior for sitrep — session-start, session-end, capture, plan-update, and handoff deliberately do not search for or move files themselves; they defer to /selfheal.
Thin wrapper (GETSITREP-10) — every check below, and every auto-fix, lives in getsitrep selfheal (src/commands/selfheal.js is the single source of truth for exact behavior and known scope boundaries; this file is a pointer to it, not a second copy of its logic).
Run:
getsitrep selfheal $ARGUMENTS
Examples: getsitrep selfheal (default checks), getsitrep selfheal deep (adds Check 5), getsitrep selfheal lock --file dashboard, getsitrep selfheal diff --file selfheal, getsitrep selfheal restore --file selfheal --force.
Print its output verbatim — do not reinterpret, re-run, or duplicate its checks yourself.
What it checks (reference — see the CLI source for exact scope)
- File Structure — sitrep/ layout, the 8 canon command files, the hash manifest. Auto-fixes what's safe to create.
- File Integrity — required sections in PROJECT_PLAN.md/STATUS_REPORT.md/MANIFEST.md, valid JSON.
- Cross-File Consistency — phase names, Active Sprint ID references, session-count drift, Current Phase sanity. Report-only.
- Progress Accuracy — recalculates progress bars and cost totals for phases it can confidently compute (skips this project's own Jira-Story-tracked phases rather than guessing).
- Codebase Sync (
deeponly) — git-tag presence for completed phases (auto-fixable), plus a best-effort commit-trace heuristic. Deliberately does not attempt "flag code not tracked in any task" — that needs an LLM's judgment, not deterministic code.
Lock/diff/restore (GETSITREP-31) — lock/unlock accept or resume monitoring on a drifted command MD; diff shows it against the canonical version shipped with the CLI; restore overwrites it with canonical, refusing without --force if it's been customized (the upgrade-protection warning). <name> is one of the 8 canon command names, not a file path.
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 · 27 lines · 0 tokens per session scan A dd051f97ffd8
selfheal is a command published in the GitHub repository viitorohit/sitrep (19 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 523 tokens. 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 2026-08-30.
Other commands, from other repositories
validate
Run the 6-gate strict quality gate on unvalidated findings.
fix-issue
Command "fix-issue" from KhaiTrang1995/claude-code-structure, covering /project:fix-issue – fix issue command, usage, description, shell steps and run tests after fix.
report-fix
Fix issues identified in a project report.
debug
Command "debug" from vignesh2027/claude-best-practice, covering /debug — systematic debugging workflow, debugging protocol, phase 1: understand the problem, phase 2: gather evidence and get relevant logs.
refactor
Command "refactor" from vignesh2027/claude-best-practice, covering /refactor — safe refactoring workflow, pre-refactor safety check, refactoring rules, change types (in safe order) and level 1: rename only.
doctor
Check OCR installation and verify all dependencies are available.