fortify SKILL.md skillA
fortify from borda/ai-rig is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add borda/ai-rig/fortify@git:20261102.52ad0ccPins git:20261102.52ad0cc in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- borda/ai-rig
- Path
plugins/cc_research/skills/fortify/SKILL.md- Versions recorded
- 19
- Latest version
- git:20261102.52ad0cc, committed Nov 2, 2026
- First version recorded
- Aug 8, 2026
- Size
- 63,291 bytes
- Repository stars
- 31
- License
- Apache-2.0
Systematic ablation study runner. After research:run finds improvements, fortify identifies component candidates from git diff + diary, creates isolated git worktrees per ablation (main repo never modified), runs metric+guard in each worktree, ranks component importance, and optionally generates reviewer Q&A calibrated to a target venue.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<objective> Ablation study runner — after `/research:run` finds improvements, fortify identifies which components contributed, generates ablation variants (remove one component at a time), runs each in **isolated git worktrees** (main repo never modified), ranks component importance, optionally generates reviewer Q&A calibrated to venue. NOT for: initial optimization loop (use `/research:run`); methodology validation (use `/research:judge`); paper-vs-code consistency (use `/research:verify`); hypothesis generation (use `research:scientist` directly). Fortify runs ablation studies on completed runs only. </objective> <constants> ```yaml MAX_ABLATION_CANDIDATES: 8 (ceiling — scientist produces 3–8; --max-ablations caps further) METRIC_TIMEOUT_MS: 360000 (6 min — deliberately larger than run's 120s/300s VERIFY_TIMEOUT_SEC, to accommodate slower ablation-variant runs) GUARD_TIMEOUT_MS: 360000 GIT_OP_TIMEOUT_MS: 15000 METRIC_RUNS_DEFAULT: 3 (metric runs per variant; --runs <N> overrides, 1–10; 1 = no σ, threshold = noise floor alone) SANITY_DIVERGENCE_PCT: 2.0 (full-variant mean vs best_metric tolerance, widened to 2σ_full; beyond it fortify aborts) …
Read the whole file at its exact version.
How to install
mdr add borda/ai-rig/fortify@sha256:caf621c696eb2be9The line at the top of this page pins the label git:20261102.52ad0cc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_sehahuviin3ybz5q)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 19 versions of this file, between Aug 8, 2026 and Nov 2, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261102.52ad0cc latest | 2026-11-02 | 52ad0cc | 63,291 B | A | view · diff |
| git:20261021.076157a | 2026-10-21 | 076157a | 63,068 B | A | view · diff |
| git:20261021.7b6ff28 | 2026-10-21 | 7b6ff28 | 61,459 B | A | view · diff |
| git:20261011.6815637 | 2026-10-11 | 6815637 | 51,123 B | A | view · diff |
| git:20261009.253fdb3 | 2026-10-09 | 253fdb3 | 51,123 B | A | view · diff |
| git:20261005.6367f83 | 2026-10-05 | 6367f83 | 50,987 B | A | view · diff |
| git:20261002.e974f38 | 2026-10-02 | e974f38 | 50,978 B | A | view · diff |
| git:20261002.381549d | 2026-10-02 | 381549d | 49,574 B | A | view · diff |
| git:20260929.98a9e77 | 2026-09-29 | 98a9e77 | 49,309 B | A | view · diff |
| git:20260923.39e3a48 | 2026-09-23 | 39e3a48 | 48,806 B | A | view · diff |
| git:20260918.3e1a63d | 2026-09-18 | 3e1a63d | 45,619 B | A | view · diff |
| git:20260912.65e8e29 | 2026-09-12 | 65e8e29 | 45,676 B | A | view · diff |
| git:20260911.be7b308 | 2026-09-11 | be7b308 | 45,507 B | A | view · diff |
| git:20260911.182df57 | 2026-09-11 | 182df57 | 45,514 B | A | view · diff |
| git:20260822.a5f4fd6 | 2026-08-22 | a5f4fd6 | 50,471 B | A | view · diff |
| git:20260821.d979319 | 2026-08-21 | d979319 | 48,725 B | A | view · diff |
| git:20260817.689cee3 | 2026-08-17 | 689cee3 | 48,709 B | A | view · diff |
| git:20260808.5143e56 | 2026-08-08 | 5143e56 | 47,643 B | A | view · diff |
| git:20260808.c2ee897 | 2026-08-08 | c2ee897 | 47,498 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (63291 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
borda/ai-rig · 31 stars · license Apache-2.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sehahuviin3ybz5q GET https://markdownregistry.com/api/v1/resolve?ref=borda/ai-rig/fortify GET https://markdownregistry.com/api/v1/blob/caf621c696eb2be93c79cc28ad948fa7a888a32ad581d5005e65260c39c6520e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.